scraping-tiktok-user-data

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external TikTok profiles and videos (such as captions, descriptions, and metadata).
  • Ingestion points: Untrusted content enters the agent's context through TikTok profile and video URLs specified in the startUrls input.
  • Capability inventory: The skill utilizes node to run local scripts, curl for network requests to the Apify API, and supports local file creation (JSON/CSV output).
  • Boundary markers: The skill does not define specific delimiters or instructions to the agent to disregard potentially malicious text embedded within the scraped TikTok data.
  • Sanitization: There is no evidence of sanitization or filtering of the scraped content before it is delivered to the agent or saved to files.
  • [COMMAND_EXECUTION]: The skill documentation provides shell commands using node and curl to interface with the Apify platform and execute a local script (run_actor.js) for data management.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external APIs on api.apify.com to trigger scraping tasks and retrieve datasets. Apify is a well-known automation and scraping service.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:36 PM
Security Audit — agent-trust-hub — scraping-tiktok-user-data