feedback-synthesizer

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

• Third-party content exposure detected (high risk: 0.85). The skill is explicitly designed to ingest and synthesize qualitative feedback from outsider-authored sources (e.g., support tickets, reviews, social media, community forums) via runtime API/data ingestion, which would feed that free-form text into the agent’s LLM context for thematic/sentiment analysis.