ClawAudit verdict
agentmemory
agentmemory-mcp
This skill configures agentmemory as a localhost MCP server (port 3111) for persistent cross-session memory in OpenClaw; all components (FastAPI, SQLite, npx) are documented and the server architecture is local-only.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
network_out
Findings (7)
Pipe-to-python pattern — remote code execution risk
SKILL.md · code · curl http://127.0.0.1:3111/agentmemory/health | python
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
References agent memory files
SKILL.md · frontmatter · MEMORY.md
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Opens WebSocket connection
SKILL.md · code · WebSocket
Popular HTTP library — network access
references/openclaw-plugin/package.json · prose · downgraded · axios
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/C). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_innetwork_out Is this flag fair?
Thanks — recorded.