ClawAudit verdict
near-agent-skills
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill appears to be a comprehensive agentic skills collection for NEAR Protocol with legitimate functionality and proper use of capabilities.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
93
security
100
transparency
100
maintenance
Permission integrity
Installs packages at runtime — transitive dependencies are not auditable
package_install
Findings (1)
Pattern match low
Popular HTTP library — network access
package-lock.json · prose · downgraded · node-fetch
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.