tiktok-product-video
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/response_io.pyutility usessubprocess.run()to execute the skill's data-fetching scripts. This pattern is part of the skill's architecture for handling large data volumes by persisting them to the file system and allowing selective extraction, which helps avoid agent context window limits. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to the NexScope proxy API to retrieve TikTok video metadata. This is a core feature of the skill and utilizes the vendor's own infrastructure.
- [PROMPT_INJECTION]: The skill processes untrusted metadata from the TikTok API, such as video descriptions and hashtags, which provides a surface for indirect prompt injection.
- Ingestion points: API response fields (
videoDesc,hashTag) retrieved byscripts/tiktok_product_video.pyand processed byscripts/response_io.py. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill has the capability to execute local scripts via
subprocessand perform network operations. - Sanitization: No sanitization or filtering of the retrieved video content is performed before it is presented to the agent.
Audit Metadata