add-workiq
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill enables the retrieval of data from Microsoft 365 services, which may include untrusted content from external sources.
- Ingestion Points: Data enters the system via the WorkIQCopilotMCPService call within the provided TypeScript connector.
- Boundary Markers: The implementation relies on standard prompt organization rather than strict delimiters or programmatic sanitization to separate retrieved context from agent instructions.
- Capability Inventory: The connector enables network-based interaction with organizational data services.
- Sanitization: The response parsing logic focuses on structural extraction but does not incorporate content-level filtering to prevent embedded instructions in external data from influencing the agent's logic.
Audit Metadata