remotion-product-demo-video

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Instructions guide the agent to execute shell commands for video rendering, still frame extraction, and quality assurance using the Remotion CLI and FFmpeg (e.g., npx remotion render, ffprobe).
  • [COMMAND_EXECUTION]: Includes a PowerShell script (scripts/validate-skill.ps1) intended for local execution to validate the skill's integrity and ensure compliance with "no-bundled-media" rules.
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of standard industry libraries from official package registries (npm, PyPI) to support video production and AI transcription tasks, referencing official documentation from well-known services.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted user-provided content such as creative briefs and word-timing transcripts.
  • Ingestion points: Intake of creative briefs and video metadata in references/production_workflow.md and processed transcripts in references/audio.md.
  • Boundary markers: Instructions do not specify the use of delimiters or boundary markers to isolate processed data from agent instructions.
  • Capability inventory: The skill utilizes extensive shell command capabilities for file manipulation, rendering, and media analysis across multiple reference files.
  • Sanitization: No explicit sanitization or filtering of external transcript text is defined before it is used to drive video composition.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 08:53 AM
Security Audit — agent-trust-hub — remotion-product-demo-video