cardano-mcp-identity

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for read-only data retrieval from a configured MCP server.
  • [SAFE]: References to external resources point to well-known services and official project repositories.
  • [SAFE]: The skill includes explicit instructions for the agent to never ask for sensitive user data such as seed phrases or private keys.
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection via external data ingestion.
  • Ingestion points: Data returned by the get_adahandles MCP tool in SKILL.md.
  • Boundary markers: The skill does not define specific boundary markers for handling tool output.
  • Capability inventory: The skill is limited to the Read tool, which minimizes the impact of potential injections.
  • Sanitization: The instructions include logic for decoding hex names and stripping specific prefixes from the retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 09:48 AM