spec-kitty-specify
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local CLI command
spec-kitty agent feature create-featureto manage project specifications. This is the intended behavior of the tool and is limited to the repository context. - [PROMPT_INJECTION]: The skill processes external user input via
$ARGUMENTS. It implements a mandatory 'Discovery Gate' interview and 'Intent Summary' confirmation to ensure user instructions are properly interpreted and sanctioned before any automated content generation or file writing occurs. - Ingestion points: External user input entering via the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: The 'Discovery Gate' and manual 'Intent Summary' confirmation act as procedural boundaries for untrusted input.
- Capability inventory: File system writes and CLI tool execution for feature management.
- Sanitization: Indirect input is sanitized through a structured paraphrasing and verification loop.
Audit Metadata