weibo-post-search

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the 'redfox.hk' API to fetch Weibo data. This is the official domain of the skill author ('redfox-data') and is used for its intended primary purpose.
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs users to manage their API keys via the 'REDFOX_API_KEY' environment variable. There are no hardcoded secrets or unsafe credential practices detected.
  • [COMMAND_EXECUTION]: The skill executes a local Python script ('user_work_list.py') with specific arguments. The script uses 'argparse' and regex-based extraction (UID) to prevent command injection from user-provided links.
  • [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were found. The skill only transmits the target UID and page number to the author's API to fulfill the user's request.
  • [PROMPT_INJECTION]: The instructions are clear and do not contain patterns attempting to bypass model safety filters or override system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 02:53 PM
Security Audit — agent-trust-hub — weibo-post-search