ClawAudit verdict

cairn

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill provides a local hybrid index for collecting and searching data, with safety gates for ingestion and no evidence of malicious behavior.

⚠ 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.

43
security
100
transparency
90
maintenance

Findings (5)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · frontmatter · http://127.0.0.1

Pattern match medium

Instructs covert action — may act without user awareness

lib/cairn/constants/cairn.constants.js · prose · downgraded · silently

Pattern match medium

Dynamic import() — loads module at runtime

lib/cairn/providers/runtimes/llama.js · prose · downgraded · import('

Pattern match medium

References child_process — can spawn system processes

lib/cairn/walk.js · prose · downgraded · child_process

Pattern match low

Popular HTTP library — network access

lib/cairn/providers/runtimes/ollama-embed.runtime.js · prose · downgraded · got

Permissions & capabilities

Requires 8 environment variables.

Is this flag fair?

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