spec-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • SAFE (SAFE): The skill consists entirely of static Markdown files. No executable code, shell commands, or network operations were detected.
  • NO_CODE (SAFE): No source code files (Python, JavaScript, etc.) are included with the skill. Markdown files contain illustrative code snippets for documentation and output purposes only, posing no execution risk.
  • Indirect Prompt Injection (SAFE): The skill defines a surface for ingesting untrusted user input via discovery questions in references/QUESTION-BANK.md. However, because the skill lacks actionable capabilities such as file system access, network requests, or code execution (eval/exec), this surface does not present a valid vulnerability.
  • Capability Review (SAFE): The inventory of capabilities across all files is limited to text interpolation and markdown rendering. No dangerous subprocess calls or sensitive file reads were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:22 PM