Caveat verdict

presidio-pii

presidio-pii-skill

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

Runs Microsoft Presidio locally via Docker to scrub PII before it reaches any AI model; all processing is local, mapping files stay local and are deleted after use, with no external data transmission beyond the intended Presidio containers.

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.

50
security
100
transparency
90
maintenance

Findings (3)

Pattern match critical

Pipe to python โ€” executes piped content as Python code

SKILL.md ยท code ยท | python3

Pattern match low

Python os.environ.get โ€” reads environment variable

scripts/presidio-restore.py ยท prose ยท downgraded ยท os.environ.get(

Pattern match low

Python urllib.request โ€” network access

scripts/presidio-scrub.py ยท prose ยท downgraded ยท urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution โ€” cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 3 system binaries. (2 elevated: curl, docker).

Is this flag fair?

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