UTC

metagpt

10 published advisories; version 0.8.2 or later fixes all but 9 of them.

Registry
PyPI
Advisories
10
Latest fix
0.8.2
Exploited in the wild
None listed
Advisories with no fix yet

9 advisories have no fixed release in any version yet. What can be done meanwhile:

General guidance from ShieldPi, not a vendor fix

Check your projects

shieldpi agent-config checks agent and MCP packages from npm and PyPI, not metagpt. Any scanner that reads the OSV database finds it in your lockfiles, for example Google's open-source OSV-Scanner.

osv-scanner scan source -r .

Or check a lockfile against ShieldMap in your browser.

Provenance

Source: github.com/geekan/metagpt, named in the package metadata (not verified)

0 of the last 10 releases of metagpt were published with build provenance: a signed record of the repository and commit each was built from, which the registry checks before it accepts the release.

  • 0.8.2
  • 0.8.1
  • 0.6.13
  • 0.6.12
  • 0.6.11
  • 0.8.0
  • 0.7.7
  • 0.7.6
  • 0.7.4
  • 0.7.3

Green: published with provenance. Grey: without.

OpenSSF Scorecard has not scored this repository.

Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-18.

Advisories
AdvisorySeverityAffectedFixed inPublished
FoundationAgents MetaGPT: Deserialization through flawed argument mapping via Message.check_instruct_content()CVE-2026-10566Low<= 0.8.2No fix yet2026-06-02
MetaGPT affected by server-side request forgery in metagpt/utils/common.pyCVE-2026-6111Low<= 0.8.2No fix yet2026-04-12
MetaGPT has an eval injection via a cross-site request forgery attackCVE-2026-6109Low<= 0.8.2No fix yet2026-04-12
MetaGPT has an eval injection in metagpt/strategy/tot.pyCVE-2026-6110Medium<= 0.8.2No fix yet2026-04-12
FoundationAgents MetaGPT vulnerable to eval injectionCVE-2026-5971Medium<= 0.8.1No fix yet2026-04-09
FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/tools/libs/terminal.pyCVE-2026-5974Medium<= 0.8.1No fix yet2026-04-09
MetaGPT has an Injection issueCVE-2026-5970Medium<= 0.8.1No fix yet2026-04-09
FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/utils/common.pyCVE-2026-5973Medium<= 0.8.1No fix yet2026-04-09
FoundationAgents MetaGPT vulnerable to os command injection via the Terminal.run_commandCVE-2026-5972Medium<= 0.8.10.8.22026-04-09
Code execution in metagptCVE-2024-23750High>= 0, <= 0.6.6No fix yet2024-01-22

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].