using-glean-code

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

• Third-party content exposure detected (high risk: 0.85). reference/exploration.md step 5 (“Read full content” via read_document) implies the agent ingests full text of top-matched files/docs from other repositories at runtime, which are outsider-authored relative to the operating user’s chosen inputs (cross-repo code/docs content).