stitch-mcp-create-project

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation and instructional bridge for the 'stitch' MCP toolset. Its primary purpose is to help the agent manage project IDs and titles within a specific workflow.
  • [SAFE]: No suspicious patterns such as prompt injection, obfuscation, or persistence mechanisms were found in the instructions or examples.
  • [SAFE]: The skill utilizes external tools (stitch, Read, Write) as defined in the platform configuration, which is standard behavior for agent skills.
  • [SAFE]: Data processing is limited to extracting numeric IDs from resource names and creating project titles from user requests, with no evidence of sensitive data harvesting or exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 10:43 AM