Caveat verdict
safe-skill-advisor
A security advisory skill that warns users about malicious skills on ClawHub, provides a 30-second self-check checklist, and recommends scanning tools; content is defensive and educational with no suspicious behavior.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (3)
Pipe-to-shell pattern (curl | sh) โ supply chain attack vector
ๆต่ฏๆฅๅ.md ยท code ยท curl | bash
Pipe to bash โ executes piped content as shell commands
ๆต่ฏๆฅๅ.md ยท code ยท | bash
Accesses .ssh directory
ๆต่ฏๆฅๅ.md ยท code ยท .ssh/
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
package_install Is this flag fair?
Thanks โ recorded.