Back to CVE records
Critical 9.8Published Sep 30, 2026
CVE-2026-51857In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced Python code through SubprocessInterpreter without an approval boundary.
Updated under an hour ago ()
Does this affect you?
It lists no affected products yet. Add what you run and Signals checks it as products are added.
EPSS puts the chance of exploitation in the next 30 days at 0.40%, higher than 33% of scored CVEs.
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced Python code through SubprocessInterpreter without an approval boundary.
- CVSS
- 9.8 CRITICAL (v3.1, CISA ADP)CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Weakness (CWE)
- CWE-94
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- 0.40% (percentile 33)
- Assigned by
- mitre
- NVD analysis
- Deferred
- Record last updated
- Oct 2, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
No affected products are listed yet.
References
- https://github.com/camel-ai/camel/issues/4037
- https://gist.github.com/Ro1ME/78606e0763520d6519897e90b305d3cd
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.