Caveat verdict

safe-skill-advisor

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

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.

โš  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.

15
security
90
transparency
90
maintenance

Permission integrity

Installs packages at runtime โ€” transitive dependencies are not auditable

package_install

Findings (3)

Pattern match critical

Pipe-to-shell pattern (curl | sh) โ€” supply chain attack vector

ๆต‹่ฏ•ๆŠฅๅ‘Š.md ยท code ยท curl | bash

Pattern match critical

Pipe to bash โ€” executes piped content as shell commands

ๆต‹่ฏ•ๆŠฅๅ‘Š.md ยท code ยท | bash

Pattern match high

Accesses .ssh directory

ๆต‹่ฏ•ๆŠฅๅ‘Š.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?

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