Unauthenticated code execution via Python eval
Published Jan 23, 2026 · Updated Jan 23, 2026
Code injection in Foundation Agents MetaGPT 0.8.1 allows remote attackers to execute arbitrary code through a crafted mapping string. The actionoutput_str_to_mapping function passes attacker-controlled mapping values to Python eval(), which interprets them as executable expressions instead of limiting them to supported type encodings. Exploitation requires no authentication and runs the supplied expression with the privileges of the MetaGPT service account.
Summary
What happened
Code injection in Foundation Agents MetaGPT 0.8.1 allows remote attackers to execute arbitrary code through a crafted mapping string. The actionoutput_str_to_mapping function passes attacker-controlled mapping values to Python eval(), which interprets them as executable expressions instead of limiting them to supported type encodings. Exploitation requires no authentication and runs the supplied expression with the privileges of the MetaGPT service account.
The record
- CVE
- CVE-2026-0761
- Published
- Jan 23, 2026
- Updated
- Jan 23, 2026
- Vendor
- Foundation Agents
- Product
- MetaGPT
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jan 23, 2026CVE publishedPublication date reported by the CVE source.
- Jan 23, 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=0.8.1
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.load mapping eval proof of conceptproof of concept · unverified
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