video-ad-specs

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the infsh command-line interface to perform operations such as authentication (infsh login) and running AI models (infsh app run). These operations are consistent with the skill's stated purpose of video ad generation using the vendor's platform.\n- [EXTERNAL_DOWNLOADS]: The skill provides links to installation instructions and supplementary resources hosted on the author's official GitHub organization repository (github.com/inference-sh/skills).\n- [SAFE]: The skill's configuration in the YAML frontmatter (allowed-tools: Bash(infsh *)) effectively implements a principle of least privilege by restricting the agent's shell execution environment to only allow the specific vendor CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 07:52 AM