project-handoff

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

• Third-party content exposure detected (high risk: 0.85). This skill’s runtime workflow uses Glean tools (e.g., search, meeting_lookup, chat) to fetch and extract content like meeting transcripts and open-item text from sources outside the operating user, which can include outsider-authored free text that is then synthesized into the agent’s LLM context.