analyzing-youtube-competitor-channel-strategy

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using node and curl. Specifically, it calls a local script scripts/run_actor.js and performs POST/GET requests to the Apify REST API to trigger scraping tasks and retrieve results.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external YouTube channels (titles, descriptions, and metadata) which is untrusted input. This data is then used to generate summaries and strategic insights.
  • Ingestion points: Data returned from the apidojo/youtube-scraper actor (SKILL.md).
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: Execution of shell commands via node and curl, and file system writes for saving results in CSV/JSON formats (SKILL.md).
  • Sanitization: No specific sanitization or filtering logic is described for the incoming YouTube data before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with api.apify.com to manage scraping jobs and download dataset items. This is a well-known service used for the skill's core functionality.
  • [DYNAMIC_EXECUTION]: The skill supports a customMapFunction parameter, which allows for the inclusion of a JavaScript string intended to be executed during the data transformation phase on the Apify platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:39 PM
Security Audit — agent-trust-hub — analyzing-youtube-competitor-channel-strategy