agent-tools
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install a CLI tool using a remote script from
https://cli.inference.sh. This is documented as the standard installation method for the service. - Evidence:
curl -fsSL https://cli.inference.sh | shfound inSKILL.md,references/authentication.md, andreferences/cli-reference.md. - Analysis: Per the trust scope rules, since the download is from the official domain of the service the skill is designed to integrate with (inference.sh), this is considered a standard functional component rather than a security risk.
- [REMOTE_CODE_EXECUTION]: The skill provides instructions to execute remote code via shell piping to install the
beltCLI. - Evidence:
curl -fsSL https://cli.inference.sh | shinSKILL.md. - Analysis: This is the intended behavior for setting up the environment. The skill also provides a manual installation method with checksum verification (
sha256sum -c checksums.txt) as a safer alternative for security-conscious users. - [COMMAND_EXECUTION]: The skill uses
Bash(belt *)to interact with the inference.sh API through the installed CLI. - Analysis: This capability is restricted to the specific CLI tool required for the skill's stated purpose of running AI applications.
Audit Metadata