spec-kitty-analyze

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local CLI command spec-kitty agent feature check-prerequisites to initialize the analysis context and retrieve file paths. This is a primary function of the skill and originates from the same author/vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from project files such as spec.md, plan.md, and tasks.md which could potentially contain malicious instructions.
  • Ingestion points: Files spec.md, plan.md, tasks.md, and /.kittify/memory/constitution.md (referenced in Step 2).
  • Boundary markers: No explicit markers are defined to isolate external file content from the system prompt.
  • Capability inventory: Execution of the spec-kitty CLI tool. No file system write operations or network communication capabilities were found.
  • Sanitization: The instructions direct the agent to create internal semantic models and explicitly forbid including raw artifact content in the final report, mitigating direct instruction leakage.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:26 AM