Skip to main content
VulnerabilityPublished Updated

CVE-2026-31236: Mycli · llm CLI tool contains a code injection vulnerability via `--functions` command-line argument

Affects mycliSource GCVE Database

0
Compare
Authoritative record:CVE-2026-31236· Critical 9.8

Not known to be exploited · CVSS 9.8 Critical : upgrade to 1.42.0 as a priority.

Data as of 17 Nov 2026, 19:19 UTC

CVSS 3.1 base score
9.8Critical
How severe the flaw is on the 0–10 CVSS scale.
Patch
Available – fixed in 1.42.0
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 12 May 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 16 Nov 2026.

What to do

Upgrade mycli to 1.42.0.

Affected software

ProductAffectedFixed in
Homebrewmyclipkg:brew/mycliOther threatsAffected
  • >=1.38.0 <1.42.0
Fixed in
  • 1.42.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

A patch is available in mycli version 1.42.0 that fixes this vulnerability. Users should upgrade to version 1.42.0 or later. Additionally, since the --functions argument executes arbitrary code by design without sandboxing, running the llm CLI tool inside a sandbox such as a container or virtual machine is recommended to reduce risk.

Description

The llm CLI tool in mycli versions 1.38.0 up to but not including 1.42.0 contains a critical code injection vulnerability via the --functions command-line argument. This argument executes arbitrary Python code without sanitization, allowing an attacker to achieve arbitrary code execution if a victim is tricked into running a crafted command. The vulnerability is local and requires user interaction. A fix is available in version 1.42.0.

References

Community reviews

Loading reviews…