tiktok-influencer-finder
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays influencer bios and descriptions from TikTok profiles, which are untrusted external sources.\n
- Ingestion points: Data is retrieved via the Apify API in
scripts/find_influencers.py.\n - Boundary markers: Untrusted content is presented in a markdown table in
SKILL.mdwithout clear boundary markers or instructions for the agent to ignore embedded commands.\n - Capability inventory: The skill's functionality is limited to data retrieval and formatting; it does not include dangerous capabilities like file system modifications or arbitrary code execution.\n
- Sanitization: Bio and content descriptions are displayed directly without filtering or sanitization.\n- [EXTERNAL_DOWNLOADS]: Fetches data from Apify, which is a well-known automation and scraping service.\n- [COMMAND_EXECUTION]: Uses a local Python script to process user parameters and interact with the Apify API.
Audit Metadata