ra-video-production-director

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts and Node.js package runners to automate production workflows. Specifically, it uses python3 automation/scripts/check_delivery.py for deliverable verification and npx hyperframes for rendering and previewing video assets.
  • [EXTERNAL_DOWNLOADS]: The skill fetches external dependencies for its rendering engine, including the GSAP animation library from the jsdelivr.net CDN and a component registry from the official repository of HeyGen (a known video AI service) on GitHub.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an intake layer for project handoff folders. It ingests untrusted data from 交接稿.md files (production contracts) to define scene units, narration, and visual styles. The skill includes built-in safeguards, such as explicit HTML escaping in its build scripts (build_index.py), to mitigate injection risks during asset generation.
  • [DYNAMIC_EXECUTION]: The production pipeline includes a template generator (build_index.py) that creates HTML-based video compositions at runtime by interpolating narration segments, timing data, and visual assets into a predefined layout.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:46 AM
Security Audit — agent-trust-hub — ra-video-production-director