ask-user-question
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious behaviors or security threats were detected during the analysis. The skill follows standard practices for developing MCP servers.
- Network Operations (SAFE): The skill performs HTTP POST requests to a local endpoint (localhost). This is a whitelisted communication pattern used to trigger UI elements in the host application (e.g., an IDE or Desktop Agent).
- Dependencies (SAFE): The project relies on official and reputable packages, including the Model Context Protocol SDK and standard TypeScript tooling.
- Indirect Prompt Injection (SAFE): While the tool displays content provided by the agent to the user, it does not ingest external untrusted data into the LLM context, posing no significant risk of indirect prompt injection.
Audit Metadata