p-video
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
beltCLI tool to interact with the inference.sh platform. Theallowed-toolsconfiguration in the frontmatter restricts the agent's shell access specifically tobeltcommands, following the principle of least privilege. - [EXTERNAL_DOWNLOADS]: The skill references installation of related skills and CLI tools from the
inference-shandbelt-shGitHub organizations and NPM namespaces. These sources are consistent with the skill's author and the service being provided. - [SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or unauthorized persistence mechanisms were detected. The skill's behavior aligns perfectly with its stated purpose of video generation.
Audit Metadata