video-ad-specs

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the belt-sh/cli and several related skills (e.g., inference-sh/skills@ai-video-generation). These resources are hosted on the author's own infrastructure or official repositories.
  • [COMMAND_EXECUTION]: Provides numerous examples of using the belt CLI to interact with the inference.sh platform for video generation, audio merging, and captioning. The allowed-tools configuration in the metadata (Bash(belt *)) correctly restricts the agent's shell access to only this specific CLI tool.
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or data exfiltration were detected. All described workflows represent standard functionality for the intended purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:48 AM
Security Audit — agent-trust-hub — video-ad-specs