Local code execution via evaluated message mapping
Published Jun 2, 2026 · Updated Jun 2, 2026
Code injection in Foundation Agents MetaGPT 0.8.2 and earlier allows local users to execute arbitrary Python code during Message loading. Message.check_instruct_content passes attacker-controlled values from the mapping branch to actionoutput_str_to_mapping, which evaluates each nonstandard value with Python eval. Exploitation requires control of serialized Message data consumed by Message.load or recovery paths and executes with the MetaGPT process privileges.
Summary
What happened
Code injection in Foundation Agents MetaGPT 0.8.2 and earlier allows local users to execute arbitrary Python code during Message loading. Message.check_instruct_content passes attacker-controlled values from the mapping branch to actionoutput_str_to_mapping, which evaluates each nonstandard value with Python eval. Exploitation requires control of serialized Message data consumed by Message.load or recovery paths and executes with the MetaGPT process privileges.
The record
- CVE
- CVE-2026-10566
- Published
- Jun 2, 2026
- Updated
- Jun 2, 2026
- Vendor
- Foundation Agents
- Product
- MetaGPT
- Classifications
- CWE-20, T1059.006
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Jun 2, 2026CVE publishedPublication date reported by the CVE source.
- Jun 2, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.8.0
- Affected versionversion=0.8.1
- Affected versionversion=0.8.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Message.check_instruct_content eval proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo