spec-kitty-checklist
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local command
spec-kitty agent feature check-prerequisites --jsonto retrieve the environment configuration and available document list. - [PROMPT_INJECTION]: The skill processes content from external files (
spec.md,plan.md,tasks.md) which may contain untrusted data. - Ingestion points: Reads requirements and technical details from
spec.md,plan.md, andtasks.mdin the feature directory. - Boundary markers: Absent. The skill does not use specific delimiters or instructions to ignore embedded prompts within the loaded files.
- Capability inventory: The skill can read local project files, create directories, and write new checklist files (
[domain].md) to the file system. - Sanitization: No sanitization or validation logic is applied to the content retrieved from the specification files before it is processed by the LLM.
Audit Metadata