wechat-title

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/fetch_official_account_trends.py to query the backend database. This is a standard and transparent implementation of its core functionality.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to https://redfox.hk/story/api/cozeSkill/getWxCozeSkillData. These communications are directed to the official domain of the skill author (redfox-data) to retrieve necessary data.
  • [CREDENTIALS_UNSAFE]: The skill utilizes the REDFOX_API_KEY environment variable for API authentication. The documentation correctly instructs users to configure this via secure environment settings and explicitly warns against hardcoding the key in code or prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 03:58 PM
Security Audit — agent-trust-hub — wechat-title