finding-youtube-channels-by-growth-rate

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from YouTube (such as channel names, video titles, and descriptions) which is external and untrusted. This content could potentially contain instructions intended to influence the agent's logic during classification or scoring steps.
  • Ingestion points: Data retrieved via the apidojo/youtube-scraper actor as described in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or boundary markers to separate untrusted external data from the agent's instructions in its output format.
  • Capability inventory: The skill uses shell execution (node, curl) to interact with the Apify API and local scripts.
  • Sanitization: No specific sanitization or filtering steps are defined for the content fetched from YouTube before it is summarized or scored.
  • [DYNAMIC_EXECUTION]: The customMapFunction input parameter accepts a JavaScript string to be used for data transformation. This provides an interface for dynamic code execution within the data processing pipeline.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to api.apify.com to trigger actor runs and retrieve datasets. This is a well-known service for web scraping and data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:45 PM
Security Audit — agent-trust-hub — finding-youtube-channels-by-growth-rate