Skip to main content
VulnerabilityPublished Updated

CVE-2026-25130: Cai framework · CAI find_file Agent Tool has Command Injection Vulnerability Through Argument Injection

Affects cai-frameworkSource GCVE Database

0
Authoritative record:CVE-2026-25130· Critical 9.7

Not known to be exploited · CVSS 9.7 Critical.

Data as of 27 Oct 2026, 17:58 UTC

CVSS 3.1 base score
9.7Critical
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.9% chance of exploitation in 30 days – higher than 59% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 30 Jan 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponised: 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 26 Oct 2026.

What to do

Affected software

ProductAffectedFixed in
PyPIcai-frameworkAffected
  • <=0.5.10
Fixed in–

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

AI-suggested

A patch addressing this vulnerability is available in the source repository but was not published to PyPI at the time of disclosure. Users should apply the patch from the repository commit e22a122 or later to remediate the issue. Until patched, avoid using the find_file() tool with untrusted input or disable it to prevent exploitation.

Description

The CAI framework's find_file tool has a command injection vulnerability due to unsanitized user input passed to a shell command with shell=True. This allows attackers to execute arbitrary commands by injecting malicious arguments such as the -exec flag. The vulnerability enables remote code execution without user approval, bypassing safety mechanisms. A patch exists but was not published to PyPI at the time of disclosure.

References

Community reviews

Loading reviews…