Caveat verdict
skincare-ai
A local skincare analysis skill explicitly declaring 100% local operation with no network library calls, strict path validation, and no data upload; consistent with described functionality.
⚠ 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 (5)
Accesses sensitive system files
path_validator.py · prose · downgraded · /etc/passwd
Uses eval() — can execute arbitrary code
RELEASE_CHECKLIST.md · prose · downgraded · eval(
Pipe to python — executes piped content as Python code
RELEASE_CHECKLIST.md · prose · downgraded · | Python
Uses exec() — may execute shell commands
RELEASE_CHECKLIST.md · prose · downgraded · exec(
subprocess execution — runs system commands from Python
RELEASE_CHECKLIST.md · prose · downgraded · subprocess.call(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). 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.