A vulnerability was found in FoundationAgents MetaGPT up to 0.8.2 and classified as critical. This affects the function Message.check_instruct_content of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization.

This vulnerability is tracked as CVE-2026-10566. The attack is restricted to local execution. Moreover, an exploit is present.

The project was informed of the problem early through an issue report but has not responded yet.