ClawAudit verdict
autoglm-open-link
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill opens web pages and extracts content without 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.
78
security
70
transparency
70
maintenance
Findings (2)
Pattern match high
HTTP request to bare IP address — common in malicious payloads
SKILL.md · frontmatter · http://127.0.0.1
Pattern match low
Python urllib.request — network access
open-link.py · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.