CVE-2026-10566 FoundationAgents MetaGPT schema.py Message.check_instruct_content deserialization
Attackers can execute arbitrary code via unsafe deserialization in MetaGPT's message handling, requiring local access.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-10566?
CVE-2026-10566 is a medium-severity unsafe deserialization vulnerability in FoundationAgents MetaGPT, published on 2 Jun 2026. It can only be exploited from the same machine or local network, with no action from the victim.
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.
Which versions are affected by CVE-2026-10566?
3 open source packages ship an affected version, including metagpt.
| Package | Affected | Fixed in |
|---|---|---|
metagpt PyPI | All versions to 0.8.2 | None |
metagpt PyPI | All versions to 0.8.2 | None |
metagpt PyPI | All versions to 0.8.2 | None |
How do I fix CVE-2026-10566?
No fix has been published for CVE-2026-10566 yet. Limit exposure of the affected software until one is available.
Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.
Is CVE-2026-10566 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-10566 exists.
Sources
Also known as GHSA-3c3g-7hwg-9qmr, PYSEC-2026-2637.