onboarding

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to use Glean chat/search/meeting_lookup to retrieve and synthesize team/project documents and meetings at runtime, which can include outsider-authored free text (e.g., wiki/issues/meeting notes/comments) that the agent then summarizes into the LLM context.