ClawAudit verdict
newspaper
The skill renders news content into an HTML page, which seems to be a legitimate and safe operation.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ 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 (4)
HTTP request to bare IP address โ common in malicious payloads
SKILL.md ยท code ยท http://127.0.0.1
fetch() โ outbound network request
SKILL.md ยท code
Makes HTTP request to external URL
SKILL.md ยท code ยท fetch('http://
Popular HTTP library โ network access
comfy-client.js ยท prose ยท downgraded ยท axios
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_out Is this flag fair?
Thanks โ recorded.