confluence

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). SKILL.md describes Confluence runtime calls (e.g., CQL search via GET /wiki/rest/api/content/search?cql=...) but does not show any required workflow that ingests outsider-authored free text from a queue/feed/inbox or auto-loads arbitrary user-submitted content without first selecting a specific item.