ClawAudit verdict
siyuan-notes-skill
The skill manages notes in 思源笔记, which matches its stated purpose.
⚠ 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.
Permission integrity
agent_memory
Findings (4)
Writes to SKILL.md — self-modifying skill
docs/Error-Recovery.md · prose · downgraded · SKILL.md), or re-run `open-doc` before each write
HTTP request to bare IP address — common in malicious payloads
README.md · code · http://127.0.0.1
Uses exec() — may execute shell commands
lib/pmf-utils.js · prose · downgraded · exec(
References agent memory files
cli.js · prose · downgraded · DailyNotes
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.