weibo-realtime-search

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to https://redfox.hk/story/api/weibo/ability/searchWork. This domain is the official API endpoint for the vendor (redfox-data) and is used for its intended search functionality.
  • [COMMAND_EXECUTION]: The skill executes a local Python script (search_weibo.py) to process search requests. It also includes instructions for setting up a standard cron job for daily automated pushes, which is a documented functional feature triggered only upon user request.
  • [CREDENTIALS_UNSAFE]: The skill correctly manages authentication by requiring the REDFOX_API_KEY environment variable. It explicitly warns against hardcoding credentials in the code or instructions, following secure development practices.
  • [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. Only the user-provided search keywords and filtering parameters are transmitted to the vendor's API.
  • [PROMPT_INJECTION]: The skill's instructions do not contain patterns designed to bypass agent safety filters or override system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 02:53 PM
Security Audit — agent-trust-hub — weibo-realtime-search