playlet-douyin-feed

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from redfox.hk. This is the official API for the vendor 'redfox-data' and is required for the skill's functionality.
  • [COMMAND_EXECUTION]: The script playlet_douyin_daily.py is executed to process content and generate reports locally; this behavior is legitimate and transparent.
  • [CREDENTIALS_UNSAFE]: The skill uses the REDFOX_API_KEY environment variable for authentication, following security best practices for credential management.
  • [DATA_EXFILTRATION]: No unauthorized data transfer was detected. The script only sends necessary query parameters to the vendor's API.
  • [PROMPT_INJECTION]: The skill processes external content from the vendor API. It provides the agent with a rigid markdown template for output, which serves as a boundary to prevent the agent from being influenced by any potential instructions embedded in the data titles.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 01:01 AM
Security Audit — agent-trust-hub — playlet-douyin-feed