Vulnerability · Published Jun 2, 2026 · Assigned by VulDB

CVE-2026-10566FoundationAgents MetaGPT schema.py Message.check_instruct_content deserialization

Medium 5.3

In plain English

A medium-severity unsafe deserialization in MetaGPT from FoundationAgents. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 2% of all known vulnerabilities).

Severity (CVSS 3.1)5.3Medium

Exploit odds (30 days)0.1%top 98.0% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. 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. The attack is restricted to local execution. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	metagpt	no fix listed	GHSA-3c3g-7hwg-9qmr
PyPI	metagpt	no fix listed	PYSEC-2026-2637

Affected products (as reported)

Vendor	Product	Versions
FoundationAgents	MetaGPT	0.8.00.8.10.8.2

Weakness: CWE-502, CWE-20 · Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R

References

VDB-367673 | FoundationAgents MetaGPT schema.py Message.check_instruct_content deserialization vdb-entry, technical-description
VDB-367673 | CTI Indicators (IOB, IOC, IOA) signature, permissions-required
CVE-2026-10566 | CVE Analysis and Report third-party-advisory
Submit #828301 | FoundationAgents MetaGPT 0.8.2 Deserialization third-party-advisory
https://github.com/FoundationAgents/MetaGPT/issues/2038 exploit, issue-tracking
https://github.com/FoundationAgents/MetaGPT/ product