legend-lore

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime workflow that “search[es] exhaustively … web, and community knowledge” and “return[s] a structured dossier with sourced claims,” which implies the agent will fetch and ingest outsider-authored public web/community text into the LLM context via its web/search tooling.