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-prerequisitesto 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, andtasks.mdwhich 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-kittyCLI 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