web-research-parallel

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime “Search”/“Extract”/“FindAll Run Result” capabilities fetch and ingest outsider-authored web page text (public web content) into the LLM context via the Gooseworks/Parallel web research pipeline (e.g., /v1beta/search, /v1beta/extract, and subsequent /result retrieval that returns model-ready content).