llm
Access large language models from the command-line
View on Github
Activity
- Latest release
- 6d ago
- Total releases
- 71
- Cadence
- ~8 days
- Last 12 months
- 16
Reach
- Stars
- 12.5k
Details
- License
- Apache-2.0
- First release
- Apr 01, 2023
| Version | Released | |
|---|---|---|
0.35
minor
| ||
0.34
minor
| ||
0.33
minor
| ||
0.32.1
patch
| ||
0.32
minor
| ||
0.32rc2
pre
| ||
0.32rc1
pre
| ||
0.31.1
patch
| ||
0.32a3
pre
| ||
0.32a2
pre
| ||
0.32a1
pre
| ||
0.32a0
pre
| ||
0.31
minor
| ||
0.30
minor
| ||
0.29
minor
| ||
0.28
minor
| ||
0.27.1
patch
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.27
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.26
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.26a1
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.26a0
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.25
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.25a0
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.24.2
patch
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.24.1
patch
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.24
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.24a1
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.24a0
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.23
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.23a0
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.22
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.21
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.20
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.19.1
patch
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.19
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.19a2
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.19a1
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.19a0
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.18
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.18a1
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.18a0
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.17.1
patch
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.17
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.17a0
pre
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.16
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.15
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.14
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.13.1
patch
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.13
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev | ||
0.12
minor
1 CVE
CVE-2026-31236
PYSEC-2026-400
GHSA-g76p-4vg5-f4qh
Jun 29, 2026
llm CLI tool contains a code injection vulnerability via `--functions` command-line argument
9.8
/ 10
Critical
Network
Low
None
None
Unchanged
High
High
High
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control. Affected versions
0.1
0.10
0.10a0
0.10a1
0.11
0.11.1
0.11.2
0.12
0.13
0.13.1
0.14
0.15
+ 43 more Show less
0.16
0.17
0.17.1
0.17a0
0.18
0.18a0
0.18a1
0.19
0.19.1
0.19a0
0.19a1
0.19a2
0.2
0.20
0.21
0.22
0.23
0.23a0
0.24
0.24.1
0.24.2
0.24a0
0.24a1
0.25
0.25a0
0.26
0.26a0
0.26a1
0.27
0.27.1
0.3
0.4
0.4.1
0.5
0.6
0.6.1
0.7
0.7.1
0.8
0.8.1
0.9
0.9a0
0.9a1
References Updated Jul 01, 2026 · Source: OSV.dev |