a2a-mcp-bridge

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill serves as a technical guide for protocol integration between Agent-to-Agent (A2A) and Model Context Protocol (MCP) ecosystems. The instructions are focused on documentation research and conceptual design.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch specification details from 'https://a2a-protocol.org/latest/specification/'. This is a legitimate resource for the described task and follows standard research procedures.
  • [PROMPT_INJECTION]: While the skill ingests untrusted data via external documentation and web searches (representing a surface for indirect prompt injection), the instructions are specifically scoped to technical protocol details, and no malicious exploitation patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 07:32 AM
Security Audit — agent-trust-hub — a2a-mcp-bridge