tiktok-shadowban-check
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external TikTok profiles, specifically captions, hashtags, and metadata.
- Ingestion points: TikTok profile data and post captions are fetched via the Apify scraper (clockworks~tiktok-profile-scraper).
- Boundary markers: There are no specified delimiters or instructions to ignore embedded commands within the processed TikTok content.
- Capability inventory: The skill executes a local Python script (
shadowban_check.py) and optionally utilizes an LLM via the OpenRouter API to analyze the content. - Sanitization: The instructions do not define any sanitization, escaping, or validation steps for the incoming social media data before it is processed or passed to the LLM.
- [COMMAND_EXECUTION]: The skill relies on the execution of a local Python script located at
../../tools/shadowban_check.py. While the script is part of the local environment, the skill's primary function is triggered by invoking this subprocess with user-supplied TikTok handles and API keys.
Audit Metadata