demand-received

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

• Third-party content exposure detected (high risk: 0.85). The required workflow reads the incoming demand document from a user-provided path (Step 1) and then extracts and includes the demand’s free-text facts/legal basis/threats into triage.md, so if the demand letter is authored by an outsider, that outsider-authored prose is ingested into the agent’s LLM context and written into the output.