A vulnerability was found in FoundationAgents MetaGPT up to 0.8.1. Impacted is the function get_mime_type of the file metagpt/utils/common.py. The manipulation results in os command injection. The attack can be executed remotely. The exploit has been made public and could be used. The project was informed of the problem early through a pull request but has not reacted yet.
Fix
Patch, vendor advisory and mitigation references on NVD 2
- https://github.com/FoundationAgents/MetaGPT/issues/1930 Exploit, Issue Tracking, Mitigation
- https://github.com/FoundationAgents/MetaGPT/pull/1983 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 00:10
Affected (CPE criteria) 1
cpe:2.3:a:deepwisdom:metagpt:*:*:*:*:*:*:*:*
References 6
- https://github.com/FoundationAgents/MetaGPT/ Product
- https://github.com/FoundationAgents/MetaGPT/issues/1930 Exploit, Issue Tracking, Mitigation
- https://github.com/FoundationAgents/MetaGPT/pull/1983 Issue Tracking, Patch
- https://vuldb.com/submit/791755 Exploit, Third Party Advisory, VDB Entry
- https://vuldb.com/vuln/356527 Third Party Advisory, VDB Entry
- https://vuldb.com/vuln/356527/cti Permissions Required