CVE-2026-51857
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced…
- Risk score
- 80/100
- CVSS
- 9.8 v3.1
- Exploit chance (30 days)
- 0.4%
- Published
- 30 Sep 2026
Open in the live forecast Today's forecast
What to know
- What it is
- 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.
- Affected
- See advisory
- Fix
- Apply the vendor's security update; see the linked advisory.
- Exploitation
- No known exploitation
Why it is Red
- CVSS 9.8 critical
- Remotely exploitable without logging in
- On your watchlist: python
References
Original description
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.
Last activity 30 Sep 2026. Patch Forecast updates every hour.