Skills
skills/inferen-sh/skills/ai-video-generation/Gen Agent Trust Hub

ai-video-generation

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh CLI tool to interact with various AI video generation models. Documented commands include infsh login, infsh app list, and infsh app run for model execution.
  • [EXTERNAL_DOWNLOADS]: References installation instructions for the infsh CLI tool hosted on the vendor's official GitHub repository (inference-sh/skills).
  • [PROMPT_INJECTION]: The skill processes untrusted external data through prompts and media URLs, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided text prompts and remote URLs for images and audio files (e.g., image_url, audio_url parameters in SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the prompt data are documented.
  • Capability inventory: Executes shell commands via the infsh tool through the allowed Bash tool scope.
  • Sanitization: No explicit sanitization or validation of input prompts or remote content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 03:50 PM