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-feature to 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 $ARGUMENTS variable in SKILL.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
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:08 PM
Security Audit — agent-trust-hub — spec-kitty-specify