confluence-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation and required workflows explicitly instruct the agent to fetch and read Confluence page bodies and search results via the REST APIs (e.g., GET /rest/api/content?expand=body.storage in references/pages.md and GET /rest/api/search?expand=content.body.storage in references/search-cql.md, and the webhooks guide which tells handlers to "call back to the REST API" for page content), which are user-generated/untrusted third‑party content that the agent is expected to interpret and that can influence subsequent actions (create/update/delete), enabling indirect prompt injection.