google-veo

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the infsh CLI tool to interact with Google's video generation models. This command execution is restricted to the specific vendor tool as defined in the allowed-tools metadata.
  • [EXTERNAL_DOWNLOADS]: The skill documentation references the installation of additional tools and skills via npx and provides links to the official inference.sh documentation. These resources are hosted on the author's verified infrastructure.
  • [SAFE]: No patterns for prompt injection, data exfiltration, obfuscation, or persistence were detected. The skill's behavior aligns with its stated purpose of providing video generation capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 10:47 PM