discussion-report-synthesizer

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

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs the agent to “Read the full conversation” (Step 1) and extract ideas from it; if that conversation includes outsider-authored messages (e.g., another participant’s chat text), that free text would be ingested into the LLM context, creating an indirect prompt-injection risk.