skills/openclaw/skills/ai-video-gen/Gen Agent Trust Hub

ai-video-gen

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The documentation describes standard integration with well-known AI services (OpenAI, Replicate, LumaAI, etc.) for media generation and local video editing.
  • [EXTERNAL_DOWNLOADS]: Fetches media assets from well-known technology companies and AI services including OpenAI, Replicate, LumaAI, Runway, and ElevenLabs. This is expected behavior for a media generation skill.
  • [PROMPT_INJECTION]: The skill processes user-supplied text prompts which are passed to external AI models, creating a standard indirect prompt injection surface. \n
  • Ingestion points: Command line arguments in generate_video.py, add_voiceover.py, and multi_scene.py. \n
  • Boundary markers: Not specified in the documentation. \n
  • Capability inventory: Subprocess calls to FFmpeg and network requests to APIs. \n
  • Sanitization: Not specified in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 12:05 AM