flock-agents

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text by reading ticket bodies from a configured issue tracker based on the user-provided SOURCE (step 1/2: “Read the SOURCE spec / parent issue” and “Pull the open tickets…reads their bodies”), then feeds that text to per-ticket implementation and verifier agents.