spec-kitty-checklist
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the local command
spec-kitty agent feature check-prerequisites --json. This is used to establish canonical project context, such as identifying the feature directory and listing available documentation files. - [PROMPT_INJECTION]: The skill ingests untrusted data from the user ($ARGUMENTS) and project-level files (spec.md, plan.md, tasks.md) to generate checklist items. This represents an indirect prompt injection surface where malicious instructions in documentation could influence the checklist generation. * Ingestion points: User-provided arguments and local feature documentation files. * Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested data. * Capability inventory: The skill can read local files, execute the spec-kitty CLI tool, and write new markdown files to the checklists/ directory. * Sanitization: There are no explicit instructions for sanitizing or escaping the content of ingested files before processing.
Audit Metadata