skills/asiaostrich/code-buddy/atdd/Gen Agent Trust Hub

atdd

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is to provide documentation and instructional templates for software development workflows. It does not execute external scripts or access sensitive system data.
  • [PROMPT_INJECTION]: The skill facilitates the processing of user-supplied content such as user stories and functional requirements, which constitutes an indirect prompt injection surface.
  • Ingestion points: User input provided via command arguments (e.g., /atdd "[story]") or content read from files processed by the agent.
  • Boundary markers: The instructions lack explicit delimiters or instructions to the agent to ignore potentially malicious directions embedded within user-provided data.
  • Capability inventory: The skill utilizes file system tools (Read, Write, Grep, Glob) to manage and search project documentation.
  • Sanitization: No input validation or sanitization of user-provided content is performed before it is added to the agent's context.
  • [SAFE]: References documentation and standards from the author's public repository (AsiaOstrich/universal-dev-standards).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 03:37 AM
Security Audit — agent-trust-hub — atdd