cli-design-expert
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied CLI documentation and designs for the purpose of auditing and refactoring, which constitutes a potential indirect prompt injection surface.
- Ingestion points: CLI command structures, help text, and output contracts provided by the user in
SKILL.md. - Boundary markers: Absent; there are no specific delimiters defined to separate user-provided content from the agent's instructions.
- Capability inventory: None; the skill does not possess any tools or scripts capable of performing file system modifications, network exfiltration, or command execution.
- Sanitization: Absent; no input validation or escaping mechanisms are described for the analyzed data.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known third-party libraries and documentation sites (such as GitHub, clig.dev, and various language-specific package registries) to assist in CLI development. These references are purely informational and point to trusted or well-known services.
Audit Metadata