scraping-youtube-trending-videos

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill relies on the execution of a remote actor on the Apify platform (apidojo/youtube-trending-scraper).
  • [DYNAMIC_EXECUTION]: The customMapFunction input parameter accepts JavaScript code intended for runtime execution within the remote scraper environment to transform output data.
  • [COMMAND_EXECUTION]: The documentation provides examples for executing a local script (node scripts/run_actor.js) to interact with the scraping service.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Fetches video titles, descriptions, and channel information directly from YouTube trending pages (SKILL.md).
  • Boundary markers: No explicit instructions to the agent to treat scraped data as untrusted or to use delimiters are provided.
  • Capability inventory: The skill has the capability to execute shell commands via local node scripts and trigger remote actor runs via REST API.
  • Sanitization: No evidence of sanitization or filtering of the scraped YouTube content before it is returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 07:22 PM
Security Audit — agent-trust-hub — scraping-youtube-trending-videos