dotnet-uno-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill integrates with an external MCP server to fetch documentation, which represents an ingestion surface for third-party content. \n
  • Ingestion points: Content is retrieved from the documentation server using the mcp__uno__uno_platform_docs_fetch tool. \n
  • Boundary markers: The instructions mandate a specific citation format to distinguish external content from internal skill knowledge. \n
  • Capability inventory: No dangerous execution capabilities (eval, subprocess calls, or system writes) are defined in the skill. \n
  • Sanitization: The skill contains a 'Safety Guidelines' section that instructs the agent to validate code examples, check version alignment, and cross-reference with project state before use. \n- [SAFE]: No security issues were identified. The skill uses legitimate tool discovery patterns and links to official documentation for the Uno Platform and the Model Context Protocol.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:31 AM
Security Audit — agent-trust-hub — dotnet-uno-mcp