didi-ride-skill

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the mcporter utility for API service calls and interacts with the host platform's CLI to persist API keys and schedule ride-tracking tasks via cron.
  • [EXTERNAL_DOWNLOADS]: The skill installs the mcporter package through the Node package manager and communicates with official API endpoints at didichuxing.com for ride and mapping services.
  • [DATA_EXFILTRATION]: User locations, destination names, and contact information are transmitted to external infrastructure as a necessary function of the ride-hailing workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user queries and the assets/PREFERENCE.md file, which is used as parameters for CLI tools and content for scheduled agent prompts. The skill incorporates human-in-the-loop confirmation steps for critical actions, such as placing or cancelling orders, to mitigate potential exploitation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:45 PM
Security Audit — agent-trust-hub — didi-ride-skill