meituan-coupon

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands and subprocess.run for environmental tasks such as identifying the Python interpreter, detecting the agent platform, and interacting with its own local data management tool (skill_cache_cli.py). This is a legitimate implementation of its data-layer functionality.
  • [EXTERNAL_DOWNLOADS]: Network operations are directed towards official Meituan API endpoints (peppermall.meituan.com) for coupon issuance, verification, and history queries. These interactions are consistent with the skill's stated purpose.
  • [SAFE]: The skill implements a robust authentication and data management system that prioritizes local storage of sensitive tokens and enforces strict rules against third-party data uploads, aligning with secure development practices. The use of cron jobs for persistence is a documented core feature for automated coupon collection.
  • [PROMPT_INJECTION]: The skill processes user-provided inputs such as phone numbers and potentially platform-provided user IDs. It instructs the agent to interpolate these into shell commands for cron job management. While this creates an indirect prompt injection surface, the risk is mitigated by hardcoded command templates and its use for the skill's primary automated functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 02:50 PM
Security Audit — agent-trust-hub — meituan-coupon