Skills
skills/inference-sh-8/skills/ai-video-generation/Gen Agent Trust Hub

ai-video-generation

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the infsh CLI tool, which is a legitimate resource owned by the vendor (inference-sh-8). Mentions of infsh login and infsh app run are standard operations for this platform.
  • [SAFE]: External links, including installation guides and documentation, point to the official inference.sh domain and the inference-sh/skills GitHub repository, which are trusted vendor locations.
  • [SAFE]: The allowed-tools configuration in the YAML frontmatter correctly restricts the agent's execution environment to only the necessary infsh command via Bash, adhering to the principle of least privilege.
  • [SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or unauthorized command execution were detected. Input parameters for video generation (like prompts and URLs) are handled within standard JSON structures for the CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:58 PM
Security Audit — agent-trust-hub — ai-video-generation