Caveat verdict
SkillPick
tiaoxuan-skill
Skill recommendation tool querying local data and GitHub/SkillHub APIs; executionSinkDetected refers to documented CLI pipeline commands matching stated purpose.
⚠ 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.
Findings (4)
Possible hardcoded credential
CLAUDE.md · code · TOKEN="ghp_xxxxxxxxx
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
CLAUDE.md · prose · downgraded · curl | bash
Pipe to bash — executes piped content as shell commands
CLAUDE.md · prose · downgraded · | bash
<script> tag in markdown — potential code injection
CLAUDE.md · prose · downgraded · <script
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). 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?
Thanks — recorded.