spec-kitty-tasks-outline

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the spec-kitty CLI tool to resolve project context and verify prerequisites, which is a standard part of its documented workflow.
  • [PROMPT_INJECTION]: The skill processes user input and project documentation (such as plan.md and spec.md), creating a surface for indirect prompt injection. Evidence Chain: 1. Ingestion points: design files and $ARGUMENTS. 2. Boundary markers: Absent. 3. Capability inventory: Execution of local CLI tools. 4. Sanitization: Absent. The risk is assessed as low due to the specialized nature of the planning task.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:08 PM