FoundationAgents MetaGPT vulnerable to os command injection via the Terminal.run_command
CVE-2026-5972 · GHSA-wp29-qmvj-frvp · published 2026-04-09 · updated 2026-04-10
- Severity
- Medium
- CVSS score
- 7.3
- Chance of exploitation (EPSS)
- 2.7%
- Fixed in
- 0.8.2
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Partial
- CISA SSVC
A vulnerability has been found in FoundationAgents MetaGPT up to 0.8.1. This issue affects the function Terminal.run_command in the library metagpt/tools/libs/terminal.py. The manipulation leads to os command injection. Remote exploitation of the attack is possible. The exploit has been disclosed to the public and may be used. The identifier of the patch is d04ffc8dc67903e8b327f78ec121df5e190ffc7b. Applying a patch is the recommended action to fix this issue.
Upgrade metagpt to 0.8.2 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| metagpt | PyPI | <= 0.8.1 | 0.8.2 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- HighCode execution in metagptmetagpt
- MediumMetaGPT has an eval injection in metagpt/strategy/tot.pymetagpt
- MediumFoundationAgents MetaGPT vulnerable to eval injectionmetagpt
- MediumFoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/tools/libs/terminal.pymetagpt
- MediumMetaGPT has an Injection issuemetagpt
- MediumFoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/utils/common.pymetagpt
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.