ClawAudit verdict
openclaw-setup-guide
nerua1-setup-guide
The skill provides a setup guide for a multi-agent AI system, which may involve sending data to external hosts for configuration and setup.
⚠ 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
package_install
agent_memory
Findings (4)
Pipe-to-python pattern — remote code execution risk
SKILL.md · prose · downgraded · curl -s <lm-studio-url>/v1/models | python
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | python3
References agent memory files
SKILL.md · code · MEMORY.md
Popular HTTP library — network access
STORY.md · prose · downgraded · Got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
agent_memorypackage_install Is this flag fair?
Thanks — recorded.