This vulnerability in FoundationAgents MetaGPT up to version 0.8.2 allows an attacker with local access to perform code injection via manipulation of an unknown function. The vulnerability has a CVSS 4.8 (medium) score with low attack complexity and requires low privileges but no user interaction. The vendor has not provided any advisory or patch, and the exploit is publicly available.

Successful exploitation allows local attackers to inject and execute arbitrary code within the affected application, potentially compromising system integrity. However, exploitation requires local access and low privileges, limiting the attack surface. There is no evidence of active exploitation in the wild.

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or vendor response is available, users should restrict local access to trusted users only and monitor for suspicious local activity related to MetaGPT until a patch is released.