discover

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

• Third-party content exposure detected (high risk: 0.75). The required workflow explicitly collects “sources” including “URLs, documents” (SKILL.md:30-31) and then “write[s] the document based on gathered sources” (SKILL.md:46-49), which implies runtime ingestion of outsider-authored free text from those external sources into the agent’s LLM context.