ClawAudit verdict

oc-doctor

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

OpenClaw health check skill running diagnostics against local installation; executionSinkDetected reflects legitimate shell diagnostics, package_install covers prerequisite tools, all purpose-appropriate.

⚠ 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.

55
security
80
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (2)

Pattern match critical

Recursive delete from root or home — destructive command

docs/user-story.en.md · code · rm -rf ~

Pattern match medium

Instructs covert action — may act without user awareness

docs/user-story.en.md · prose · downgraded · quietly

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 system binaries.

package_installagent_memory

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API