ai-friendly-cli
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a technical guide for security-conscious developers.
- [PROMPT_INJECTION]: Mentions of phrases such as 'ignore previous instructions' are included strictly as examples of patterns that a secure CLI should identify and sanitize from user-generated content before returning it to an agent.
- [DATA_EXFILTRATION]: Examples of sensitive paths like
/etc/passwdand~/.ssh/id_rsaare provided to teach the implementation of path traversal validation and input hardening. - [CREDENTIALS_UNSAFE]: The documentation emphasizes avoiding the exposure of secrets, providing implementation patterns for masking tokens and using secure credential storage like OS keyrings.
Audit Metadata