stakeholders

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow uses runtime “search”/“code_search”/“employee_search” (and Glean chat) to retrieve and synthesize information from external sources (e.g., docs, RFCs, code ownership records, employee/team data), which can include outsider-authored free text that the agent then feeds into its LLM context.