google-veo

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and documentation from the inference-sh public GitHub repository to set up the necessary CLI environment.- [COMMAND_EXECUTION]: The skill instructs the agent to execute the 'belt' CLI tool for authenticating, searching for available models, and running video generation tasks.- [PROMPT_INJECTION]: The skill processes untrusted user input via video generation prompts. Evidence: 1. Ingestion points: '--input' JSON arguments in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: Executes the 'belt' command via Bash tool. 4. Sanitization: None described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — google-veo