design-doc-interviewer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • SAFE (SAFE): The skill performs intended documentation tasks without any malicious behavior. It uses standard markdown templates and a question bank to guide the user through a design interview.
  • Indirect Prompt Injection (SAFE): Analyzed the potential for indirect prompt injection from repository context.
  • Ingestion points: Context is gathered from files in design/* and design/ideas/ as specified in SKILL.md.
  • Boundary markers: Absent; however, the agent is instructed to summarize findings and confirm them with the user, which provides a layer of human review.
  • Capability inventory: The skill is limited to reading local files and writing markdown documentation to design/{package}/.
  • Sanitization: Content is processed into a summarized form before being added to the final document.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM