NYC

tdd-obra

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill contains only Markdown documentation and metadata. There are no Python scripts, shell commands, or other executable artifacts provided.
  • PROMPT_INJECTION (SAFE): The instructions define a TDD workflow (Red-Green-Refactor). There are no attempts to override system prompts, bypass safety filters, or use adversarial roleplay.
  • DATA_EXFILTRATION (SAFE): No network operations, file system access patterns, or sensitive credential patterns were detected.
  • EXTERNAL_DOWNLOADS (SAFE): While the metadata references an external GitHub repository (obra/superpowers), the skill does not attempt to download or execute any remote content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:20 PM