A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. 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.
Fix
Patch, vendor advisory and mitigation references on NVD 1
- https://github.com/FoundationAgents/MetaGPT/pull/1946 Issue Tracking, Patch
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 5.5 · deepwisdomNVD modified 2026-10-26 21:10
Affected (CPE criteria) 2
cpe:2.3:a:deepwisdom:metagpt:0.8.0:*:*:*:*:*:*:*cpe:2.3:a:deepwisdom:metagpt:0.8.1:*:*:*:*:*:*:*
References 6
- https://github.com/FoundationAgents/MetaGPT/ Product
- https://github.com/FoundationAgents/MetaGPT/issues/1933 Issue Tracking
- https://github.com/FoundationAgents/MetaGPT/pull/1946 Issue Tracking, Patch
- https://vuldb.com/submit/791761 Exploit, Third Party Advisory, VDB Entry
- https://vuldb.com/vuln/356970 Third Party Advisory, VDB Entry
- https://vuldb.com/vuln/356970/cti Permissions Required