skills/acedatacloud/skills/didi-ride/Gen Agent Trust Hub

didi-ride

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements safety gates using a --confirm flag for high-impact operations such as taxi_create_order and taxi_cancel_order. This ensures the agent must obtain explicit user confirmation before performing actions that involve real money or service requests.
  • [SAFE]: The Python helper script (didi.py) is written using only standard libraries, avoiding external dependencies. It includes specific logic to ensure the DIDI_MCP_KEY environment variable is never printed to standard output or exposed in error tracebacks.
  • [SAFE]: Network communications are limited to appropriate endpoints for the skill's purpose, including DiDi's official services (mcp.didichuxing.com) and the vendor's own authentication infrastructure (auth.acedata.cloud).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 06:41 PM
Security Audit — agent-trust-hub — didi-ride