social-signal-research

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly collects public community signals from outsider-authored sources (e.g., forums, X, Product Hunt, HN) by fetching pages/threads and extracting paraphrased evidence, which becomes readable text in the agent’s LLM context at runtime.