user-identify

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow may perform Web Search and then ingest scraped/third-party free-text evidence (e.g., competitor pages, community discussions, user reviews) into research/02-users-research.md and 02-users.md, which is then included in the agent’s LLM context—an outsider-authored free-text injection surface.