CVE-2026-10566: Deserialization in FoundationAgents MetaGPT
FoundationAgents MetaGPT versions 0.8.0 through 0.8.2 contain a deserialization vulnerability in the Message.check_instruct_content function. This flaw allows manipulation of argument mapping leading to unsafe deserialization. Exploitation requires local access and no user interaction. No official fix or vendor response is currently available. The vulnerability has a medium severity rating with a CVSS score of 4.8.
AI Analysis
Technical Summary
CVE-2026-10566 is a deserialization vulnerability in FoundationAgents MetaGPT affecting versions 0.8.0 through 0.8.2. The issue exists in the Message.check_instruct_content function within metagpt/schema.py, where manipulation of the argument mapping enables unsafe deserialization. Exploitation requires local access with low privileges and no user interaction. The vulnerability has been publicly disclosed but no official patch or remediation guidance has been provided by the vendor as of the publication date.
Potential Impact
Successful exploitation could allow an attacker with local access to manipulate deserialization processes, potentially leading to code execution or other impacts related to unsafe deserialization. The CVSS score of 4.8 indicates a medium severity impact with limited attack vector (local), low complexity, and no user interaction required.
Mitigation Recommendations
No official fix or vendor advisory is currently available. Users should monitor vendor communications for updates. Until a patch is released, restrict local access to trusted users only and consider additional controls to limit exposure to this vulnerability.
CVE-2026-10566: Deserialization in FoundationAgents MetaGPT
Description
FoundationAgents MetaGPT versions 0.8.0 through 0.8.2 contain a deserialization vulnerability in the Message.check_instruct_content function. This flaw allows manipulation of argument mapping leading to unsafe deserialization. Exploitation requires local access and no user interaction. No official fix or vendor response is currently available. The vulnerability has a medium severity rating with a CVSS score of 4.8.
CVSS v4.0
Score 4.8medium
Affected software
pkg:github/foundationagents/MetaGPTRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-10566 is a deserialization vulnerability in FoundationAgents MetaGPT affecting versions 0.8.0 through 0.8.2. The issue exists in the Message.check_instruct_content function within metagpt/schema.py, where manipulation of the argument mapping enables unsafe deserialization. Exploitation requires local access with low privileges and no user interaction. The vulnerability has been publicly disclosed but no official patch or remediation guidance has been provided by the vendor as of the publication date.
Potential Impact
Successful exploitation could allow an attacker with local access to manipulate deserialization processes, potentially leading to code execution or other impacts related to unsafe deserialization. The CVSS score of 4.8 indicates a medium severity impact with limited attack vector (local), low complexity, and no user interaction required.
Mitigation Recommendations
No official fix or vendor advisory is currently available. Users should monitor vendor communications for updates. Until a patch is released, restrict local access to trusted users only and consider additional controls to limit exposure to this vulnerability.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-06-01T16:34:26.724Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a1e40ffe29bf47b506f6ba6
Added to database: 06/02/2026, 02:33:35 UTC
Last enriched: 07/10/2026, 10:23:58 UTC
Last updated: 07/31/2026, 19:22:57 UTC
Views: 57
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.