product-feasibility-scout

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow is “research” and “cite sources” but no required step is specified that ingests outsider-authored free text without first selecting a specific, targeted item; it primarily relies on first-party documentation/blog/regulatory texts (per the instructions and templates), so there’s no clear indirect-prompt-injection queue/feed or arbitrary user-content ingestion path described.