dotnet-uno-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process external content retrieved via the Uno Platform MCP server tools.
  • Ingestion points: The skill utilizes mcp__uno__uno_platform_docs_search and mcp__uno__uno_platform_docs_fetch within the SKILL.md file to retrieve external documentation into the agent's context.
  • Boundary markers: The skill provides clear instructions under 'Citation Requirements' and 'Safety Guidelines' to distinguish external data and validate code, though it lacks technical delimiters for the fetched content.
  • Capability inventory: This skill does not contain any scripts, subprocess calls, file-write operations, or network requests directly within its own code; it acts purely as an instruction set for external tools.
  • Sanitization: The skill includes explicit instructions for the agent to 'Validate code suggestions before acting' and 'Treat MCP content as advisory,' placing the responsibility for sanitization on the agent's reasoning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 03:43 PM