douyin-content-surge
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill requires a
REDFOX_API_KEYenvironment variable and makes HTTPS requests toredfox.hk. These operations are consistent with the skill's purpose of fetching data from the vendor's service.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests video titles and author names from the Douyin API. \n - Ingestion points: API data received in
scripts/douyin_daily_increment.py.\n - Boundary markers: None defined in the agent instructions.\n
- Capability inventory: The agent executes a script that performs network I/O.\n
- Sanitization: The Python script replaces Markdown-sensitive characters (like
|,[,]) in retrieved titles to prevent table layout manipulation.\n- [COMMAND_EXECUTION]: The skill includesscripts/douyin_daily_increment.py, which is executed by the agent. The script uses standard libraries and performs only the necessary tasks to query the API and format the results.
Audit Metadata