ClawAudit verdict
siyuan-llm-wiki
A knowledge management skill that maintains structured notes in a local SiYuan instance via its local HTTP API; all network calls are to 127.0.0.1 and behavior is consistent with the stated LLM-maintained wiki workflow.
⚠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
network_out
Findings (3)
Possible hardcoded credential
examples/api-calls.md · code · TOKEN="ä½ çš„API Token
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
Python os.environ.get — reads environment variable
scripts/siyuan_api.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
network_out Is this flag fair?
Thanks — recorded.