Caveat verdict

arxiv-paper-reviews

weak-accept

45
๐ŸŸ  Risky
Significant risk patterns flagged โ€” automated deep scan, not behavioral proof.

All API calls go to a hardcoded private IP (150.158.152.82:8000) for an undisclosed arXiv crawler service, sending user data to an unverifiable third-party server with no public identity.

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
40
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime โ€” transitive dependencies are not auditable

package_install

Findings (2)

Pattern match high

HTTP request to bare IP address โ€” common in malicious payloads

SKILL.md ยท frontmatter ยท http://150.158.152.82

Pattern match medium

pip3 install โ€” installs Python packages at runtime

SKILL.md ยท code ยท pip3 install

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

No declared permissions โ€” minimal attack surface.

package_installcredential_access

Is this flag fair?

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