creating-mcp-agent-evals

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for running various development and maintenance commands through the terminal. Evidence includes commands in reference.md for executing evaluation suites with pnpm, managing remote datasets via npx langfuse-cli, and running local probe scripts with tsx.\n- [INDIRECT_PROMPT_INJECTION]: The evaluation framework described in the skill ingests user-provided text prompts to test agent behavior, creating a surface for indirect prompt injection. \n
  • Ingestion points: The input.query field in the Langfuse dataset item shape described in reference.md. \n
  • Boundary markers: No explicit boundary markers or instruction-override directives are specified for the query input. \n
  • Capability inventory: The harness executes MCP tool calls and can run local shell commands. \n
  • Sanitization: No specific sanitization or filtering of the user queries is mentioned, as the purpose is to evaluate model responses to arbitrary natural language. \n- [SAFE]: The skill follows standard security practices by instructing users to store credentials in .env files rather than hardcoding them. All external domains and repositories mentioned are either vendor-owned (e.g., langfuse.apify.dev) or recognized technology services (e.g., rfc-editor.org, example.com).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 07:25 AM
Security Audit — agent-trust-hub — creating-mcp-agent-evals