Caveat verdict

global-biblio-base

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

This is a legitimate academic literature search skill that reads API config and calls a documented SmartLib gateway for bibliographic searches; the network access and credential reading are transparently described and serve the stated purpose.

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.

78
security
80
transparency
90
maintenance

Findings (2)

Pattern match high

subprocess execution โ€” runs system commands from Python

PIPELINE.md ยท code ยท subprocess.run(

Pattern match low

Python urllib.request โ€” network access

PIPELINE.md ยท prose ยท downgraded ยท urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). 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.

network_in

Is this flag fair?

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