Browse / Improper Output Handling / CVE-2026-5971
FoundationAgents MetaGPT vulnerable to eval injection
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- metagpt (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
Model-generated XML content is passed into eval during ActionNode.xml_fill, so crafted model output causes arbitrary code to run on the server. (Our summary, written by a model. The source text is below.)
Details
A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xml_fill of the file metagpt/actions/action_node.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated code. The attack may be launched remotely. The exploit has been published and may be used. The project was informed of the problem early through a pull request but has not reacted yet.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-5971
- https://github.com/FoundationAgents/MetaGPT/issues/1928
- https://github.com/FoundationAgents/MetaGPT/issues/1956
- https://github.com/FoundationAgents/MetaGPT
- https://vuldb.com/submit/791734
- https://vuldb.com/vuln/356525
- https://vuldb.com/vuln/356525/cti
Source: GitHub Advisory Database, used under CC BY 4.0.