spot-people-engaging-with-competitors

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly asks for a LinkedIn profile URL and uses the OpenFunnel API (e.g., bash "$API" POST /api/v1/signal/... and get-signal-list) to fetch and present engagement data derived from public LinkedIn posts/comments (user-generated third‑party content), which the agent is expected to read and act on (deploy signals), creating a clear avenue for indirect prompt injection.