web-search-plus

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the skill calls outsider web-search providers (e.g., Serper/Tavily/Exa/You.com/SearXNG) and ingests their returned readable text fields like answer, snippet, and optionally raw_content into the JSON result that is then available for the agent/LLM context (indirect prompt-injection via provider-supplied page text).