Vulnerability · Published Apr 9, 2026 · Assigned by VulDB

CVE-2026-5970FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection

High 7.3

In plain English

A high-severity code injection in MetaGPT from FoundationAgents. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 35% of all known vulnerabilities).

Severity (CVSS 3.1)7.3High

Exploit odds (30 days)0.4%top 65.3% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	metagpt	no fix listed	GHSA-g977-h85w-h2xj
PyPI	metagpt	no fix listed	PYSEC-2026-2640

Affected products (as reported)

Vendor	Product	Versions
FoundationAgents	MetaGPT	0.8.00.8.1

Weakness: CWE-94, CWE-74 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R

References

VDB-356524 | FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection vdb-entry, technical-description
VDB-356524 | CTI Indicators (IOB, IOC, TTP, IOA) signature, permissions-required
Submit #791693 | FoundationAgents MetaGPT 0.8.1 Code Injection (CWE-94) third-party-advisory
https://github.com/FoundationAgents/MetaGPT/issues/1942 exploit, issue-tracking
https://github.com/FoundationAgents/MetaGPT/pull/1988 issue-tracking, patch
https://github.com/FoundationAgents/MetaGPT/ product