research-lookup

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

• Third-party content exposure detected (high risk: 0.85). The skill sends the user’s query to external web-search backends (Parallel Chat API / Perplexity via OpenRouter), which at runtime fetch and summarize public web/academic content; those retrieved outsider-authored texts can be included in the model’s generated response that is then returned and placed into the agent’s LLM context.