requirements-interlock

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

• Third-party content exposure detected (high risk: 0.85). The required workflow reads docs/user-stories/* (user story text authored by an outsider relative to the operating user) and then summarizes/extracts it into the TRI.md Context, which becomes LLM-readable prose in the agent’s context during the “Read all inputs” step.