Browse / Improper Output Handling / CVE-2026-5970
MetaGPT has an Injection issue
- 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
Manipulated solution text reaches the benchmark's check routine unsanitised and is executed as code during evaluation. (Our summary, written by a model. The source text is below.)
Details
A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public 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-2026-5970
- https://github.com/FoundationAgents/MetaGPT/issues/1942
- https://github.com/FoundationAgents/MetaGPT/pull/1988
- https://github.com/FoundationAgents/MetaGPT
- https://vuldb.com/submit/791693
- https://vuldb.com/vuln/356524
- https://vuldb.com/vuln/356524/cti
Source: GitHub Advisory Database, used under CC BY 4.0.