sota-cli-ux
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is a collection of Markdown documentation files providing UX and technical guidance for CLI developers. It does not include any scripts, executables, or configurations that perform actions on the system.
- [NO_CODE]: The skill does not deliver any functional code or dependencies. Its content is purely instructional and intended to be read by an agent or human.
- [DATA_EXPOSURE]: The documentation prioritizes security by recommending that secrets never be passed via command-line arguments (argv) to avoid leakage in shell history or process monitors.
- [INDIRECT_PROMPT_INJECTION]: The skill describes an 'AUDIT mode' that directs an agent to execute and analyze external CLI tools. This creates an inherent attack surface for indirect prompt injection from those tools' outputs. 1. Ingestion points: Command-line output from the tools being audited (SKILL.md). 2. Boundary markers: No specific delimiters are mandated in the auditing instructions. 3. Capability inventory: The agent is assumed to have shell capability to run the tools. 4. Sanitization: No sanitization is performed by the skill itself, though it includes rules for tool authors to sanitize output (CWE-150) to mitigate terminal escape attacks.
Audit Metadata