Remote command execution via LLM-exposed Bash tool
Published Apr 9, 2026 · Updated Apr 9, 2026
OS command injection in Foundation Agents MetaGPT 0.8.0 through 0.8.1 allows remote attackers to execute commands via LLM prompt injection. The registered Bash.run tool passes an LLM-supplied command through run_command, which writes it unfiltered to a persistent Bash process. Exploitation requires a MetaGPT workflow that exposes the Bash tool to an LLM and permits attacker-controlled content to influence the model; commands run with the MetaGPT process privileges.
Summary
What happened
OS command injection in Foundation Agents MetaGPT 0.8.0 through 0.8.1 allows remote attackers to execute commands via LLM prompt injection. The registered Bash.run tool passes an LLM-supplied command through run_command, which writes it unfiltered to a persistent Bash process. Exploitation requires a MetaGPT workflow that exposes the Bash tool to an LLM and permits attacker-controlled content to influence the model; commands run with the MetaGPT process privileges.
The record
- CVE
- CVE-2026-5974
- Published
- Apr 9, 2026
- Updated
- Apr 9, 2026
- Vendor
- Foundation Agents
- Product
- MetaGPT
- Classifications
- CWE-77, CWE-78, T1059.004
- 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?
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
- Bash.run 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