GitHub Advisoryadvisory · PyPI
GHSA-xr7v-m9px-q4qj MetaGPT has an eval injection in metagpt/strategy/tot.py
MEDIUM
Official page ↗
- Aliases
- CVE-2026-6110
- Ecosystem
- PyPI
- Packages
- metagpt
- Severity
- Moderate
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
- Weaknesses
- CWE-74
- Reviewed
- 2026-04-14
Affected packages
• PyPI metagpt: <= 0.8.2 (no fix yet)
Description
A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function generate_thoughts of the file metagpt/strategy/tot.py of the component Tree-of-Thought Solver. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit is publicly available and might be used. The project was informed of the problem early through an issue report but has not responded yet.
Related
Alias · CVE (1)
- CVE-2026-6110 A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. vulnerability
Weakness · CWE (1)
- CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component weakness
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-6110 advisory
- https://github.com/FoundationAgents/MetaGPT/issues/1933 web
- https://github.com/FoundationAgents/MetaGPT/pull/1946 web
- https://github.com/FoundationAgents/MetaGPT package
- https://vuldb.com/submit/791761 web
- https://vuldb.com/vuln/356970 web
- https://vuldb.com/vuln/356970/cti web