CVE-2026-5970High· 7.3▾ TwilightMetaGPT has an Injection issue
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 40.2 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Jul 13.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via OSV
Last analysed / modified upstream
0.4%
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.
metagpt <= 0.8.1Refer to the advisory for the patched release.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-6110High· 7.3MetaGPT has an eval injection in metagpt/strategy/tot.py
CVE-2026-5972High· 7.3FoundationAgents MetaGPT vulnerable to os command injection via the Terminal.run_command
CVE-2026-6109Medium· 4.3MetaGPT has an eval injection via a cross-site request forgery attack
CVE-2026-6111Medium· 6.3MetaGPT affected by server-side request forgery in metagpt/utils/common.py
CVE-2026-5973High· 7.3FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/utils/common.py
CVE-2026-5974High· 7.3FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/tools/libs/terminal.py