content-analytics-engine

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow fetches PostBridge API data (e.g., GET /v1/posts?limit=100 for post captions and GET /v1/analytics?limit=100), and those API-delivered text fields can include outsider-authored free text (captions/comments) that is then ingested into the LLM context via the generated markdown/JSON reports.