Code execution via eval of LLM output
Published Apr 9, 2026 · Updated Apr 9, 2026
Code injection in MetaGPT 0.8.0 through 0.8.1 allows remote attackers to execute Python code through manipulated LLM output. The ActionNode.xml_fill method extracts list or dictionary fields from XML-formatted model responses and passes their raw text directly to eval(). Exploitation requires control over, or successful prompt injection into, an LLM response processed by such a field and executes with the MetaGPT process's privileges.
Summary
What happened
Code injection in MetaGPT 0.8.0 through 0.8.1 allows remote attackers to execute Python code through manipulated LLM output. The ActionNode.xml_fill method extracts list or dictionary fields from XML-formatted model responses and passes their raw text directly to eval(). Exploitation requires control over, or successful prompt injection into, an LLM response processed by such a field and executes with the MetaGPT process's privileges.
The record
- CVE
- CVE-2026-5971
- Published
- Apr 9, 2026
- Updated
- Apr 9, 2026
- Vendor
- Foundation Agents
- Product
- MetaGPT
- Classifications
- CWE-95, CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 9, 2026CVE publishedPublication date reported by the CVE source.
- Apr 9, 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?
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
- ActionNode.xml_fill prompt-injection 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