youtube-retention-script-builder

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local utility script ..\_shared\scripts\youtube_growth_automation.py to perform hook scoring, script planning, and report generation.- [EXTERNAL_DOWNLOADS]: The collect-videos command is used to fetch data from YouTube URLs, which is a well-known service.- [PROMPT_INJECTION]: The skill processes content from external YouTube videos, which represents an indirect prompt injection surface.
  • Ingestion points: Data is ingested via the --video parameter in the collect-videos command (SKILL.md).
  • Boundary markers: The instructions do not provide explicit delimiters or "ignore instructions" warnings to help the agent distinguish between its core logic and external video content.
  • Capability inventory: The agent can execute local Python scripts and perform file system writes (.json, .html).
  • Sanitization: There is no evidence of content filtering or sanitization being applied to the external data before it is integrated into the agent's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:19 PM