mcp-tester
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and documentation are purely functional, focused on evaluating MCP tool quality and performance. No evidence of unauthorized command execution, credential harvesting, or data exfiltration was found.
- [PROMPT_INJECTION]: The skill creates an ingestion point for external data by processing responses from MCP tools during Phase 4 (Test Execution) and Phase 5 (Rating & Feedback). This presents an indirect prompt injection surface. However, the risk is minimized by the skill's explicit requirement for user confirmation before executing any mutating tools (create, update, delete operations), ensuring human oversight for potentially harmful actions.
Audit Metadata