skills/inference-sh/skills/google-veo/Gen Agent Trust Hub

google-veo

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool, which is the official interface for the inference.sh platform. The commands provided (belt login, belt app run) are standard operations for this service.
  • [EXTERNAL_DOWNLOADS]: All external links and installation references point to official vendor domains (inference.sh) or the author's official GitHub repository (github.com/inference-sh). These are used for documentation and legitimate skill management.
  • [PROMPT_INJECTION]: Analysis of the instructions and examples shows no attempts to override agent safety protocols or hijack the system prompt.
  • [DATA_EXFILTRATION]: No patterns of unauthorized data collection or exfiltration were found. Network activity is limited to the expected interaction with the vendor's API.
  • [REMOTE_CODE_EXECUTION]: There are no instances of arbitrary code execution or scripts being downloaded and executed from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 10:45 AM
Security Audit — agent-trust-hub — google-veo