Remote code execution via unvalidated LLM eval
Published Apr 12, 2026 · Updated Apr 12, 2026
Code injection in MetaGPT 0.8.0 and 0.8.1 allows remote attackers to execute arbitrary Python code through crafted Tree-of-Thought input. The generate_thoughts function in metagpt/strategy/tot.py extracts a code block from the model response and passes it directly to eval without validation. Exploitation requires attacker-controlled input to influence the configured model's response; successful code runs with the MetaGPT process's privileges.
Summary
What happened
Code injection in MetaGPT 0.8.0 and 0.8.1 allows remote attackers to execute arbitrary Python code through crafted Tree-of-Thought input. The generate_thoughts function in metagpt/strategy/tot.py extracts a code block from the model response and passes it directly to eval without validation. Exploitation requires attacker-controlled input to influence the configured model's response; successful code runs with the MetaGPT process's privileges.
The record
- CVE
- CVE-2026-6110
- Published
- Apr 12, 2026
- Updated
- Apr 12, 2026
- Vendor
- Foundation Agents
- Product
- MetaGPT
- Classifications
- CWE-94, CWE-74, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 12, 2026CVE publishedPublication date reported by the CVE source.
- Apr 12, 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
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
- MetaGPT Tree-of-Thought eval-injection PoCproof 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