ai-dev-workflow

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard software development and verification commands.
  • Evidence: Instructions include running npx tsc --noEmit, npx jest, and npx cucumber-js to validate implementation against specifications.
  • Context: These operations are restricted to the local development environment and are essential for the skill's primary purpose of behavior-driven development and automated testing.
  • [PROMPT_INJECTION]: The workflow incorporates an indirect ingestion surface by reading external project documentation files (SPEC.md, AGENTS.md, and .feature files).
  • Ingestion points: Project specification files and Gherkin feature definitions located in the repository.
  • Boundary markers: The skill uses a structured 'Phase' approach to separate understanding, planning, and implementation steps, though it does not define explicit delimiters for content within the specification files.
  • Capability inventory: The agent possesses the capability to execute shell commands and modify source code based on the instructions found in the ingested files.
  • Sanitization: The workflow relies on the agent's interpretation and user review of the generated plans and code modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 02:40 PM