Caveat verdict

deadclaw

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill has privileged access to halt all running agents, pause scheduled jobs, kill active sessions, and log everything, which could be risky if not properly controlled.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

75
security
90
transparency
90
maintenance

Findings (4)

Pattern match medium

Uses exec() — may execute shell commands

SKILL.md · prose · downgraded · exec(

Pattern match medium

Instructs covert action — may act without user awareness

deadclaw/docs/launch-post.md · prose · downgraded · quietly

Pattern match low

Popular HTTP library — network access

deadclaw/docs/android-widget-guide.md · prose · downgraded · got

Pattern match low

Opens WebSocket connection

deadclaw/docs/roadmap.md · prose · downgraded · WebSocket

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

No declared permissions — minimal attack surface.

Is this flag fair?

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