stitch-mcp-create-project
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard procedural instructions for an AI agent to interface with the Stitch MCP toolset. No indicators of prompt injection, data exfiltration, or malicious persistence were found.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to generate descriptive project titles. This data flow is restricted to a simple labeling task within a tool argument and does not present a significant security risk.
Audit Metadata