ClawAudit verdict

Confluence Integration

lukaizj-confluence

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

A standard Confluence REST API integration using curl with user-supplied credentials stored in environment variables; credentials are used only for the declared Confluence instance and the skill explicitly states they are never exposed externally.

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.

100
security
90
transparency
70
maintenance

No red flags detected in static analysis.

Checked: 115 threat patterns ยท AST capability extraction ยท cross-zone compound shapes ยท permission integrity.

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution โ€” cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

Was this verdict right?

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