Caveat verdict

paper-fetch

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Academic paper PDF downloader using Unpaywall, Semantic Scholar, arXiv, PMC, and Sci-Hub; the auto-update step is a transparent git pull documented in the skill itself.

⚠ 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.

35
security
90
transparency
70
maintenance

Findings (6)

Pattern match critical

Pipe to python — executes piped content as Python code

README_CN.md · code · | python

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · Silently

Pattern match medium

Accesses shell history/config

README_CN.md · prose · downgraded · ~/.zshrc

Pattern match medium

Gopher protocol — SSRF attack vector

scripts/fetch.py · prose · downgraded · gopher://

Pattern match low

Python urllib.request — network access

scripts/fetch.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/fetch.py · prose · downgraded · os.environ.get(

Permissions & capabilities

Requires 1 system binary.

Is this flag fair?

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