glean-cli

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill is invoking the local glean CLI (e.g., glean search/chat/documents/...), which fetches and returns enterprise documents and chat citations from the user’s Glean tenant; those returned document texts are outsider-authored content (not authored by the operating user) that the agent then ingests into the LLM context via the CLI output.