installing-cli-tools
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill implements strong negative constraints to prevent secret leakage. It explicitly forbids the agent from reading, printing, or searching for existing secrets in files like
.env, SSH keys, or cloud credential stores. It recommends secure authentication flows such as OAuth or OS-native credential stores (e.g., macOS Keychain). - [COMMAND_EXECUTION]: The instructions provide a framework for executing installation commands safely. It advises using standard package managers, verifying binary checksums, and reviewing installer scripts locally rather than piping network content directly to a shell.
- [DATA_EXFILTRATION]: The skill includes instructions to avoid putting sensitive values in command arguments, shell history, or chat logs, which mitigates the risk of accidental data exposure.
- [REMOTE_CODE_EXECUTION]: While the skill's purpose is to install software (which involves remote code), it mandates using official documentation and trusted sources, and recommends against insecure practices like unverified script execution.
Audit Metadata