playlet-gzh-feed

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves article metrics and metadata from https://redfox.hk, which is the official API for the vendor 'redfox-data'. This network activity is restricted to the skill's documented functionality.
  • [CREDENTIALS_UNSAFE]: The skill appropriately manages sensitive access by requiring the REDFOX_API_KEY to be set as an environment variable. No secrets or API keys are hardcoded in the source code.
  • [COMMAND_EXECUTION]: Local Python scripts (assets/daily_report.py and scripts/playlet_gzh_daily.py) are used for data processing and report generation. These scripts rely on standard Python libraries and do not perform any privileged or suspicious operations.
  • [DATA_EXFILTRATION]: Data access is limited to the results of the API queries. No evidence was found of the skill attempting to access or transmit sensitive system files or private user information.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 12:31 PM
Security Audit — agent-trust-hub — playlet-gzh-feed