deep-interview

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the scope of user interaction and local file management for documentation purposes. No high-risk behaviors or suspicious patterns were detected.
  • [DATA_EXPOSURE]: The skill writes information to the ~/Documents/interviews/ directory. This is consistent with its stated purpose of building a knowledge base and does not involve accessing sensitive system directories or private credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input and writes it to files.
  • Ingestion points: User responses received via the AskUserQuestion tool.
  • Boundary markers: The skill uses markdown headers and blockquotes to structure the output.
  • Capability inventory: The skill uses file-writing and folder creation to organize knowledge.
  • Sanitization: Content is structured into markdown files but not explicitly sanitized; however, as the skill does not read these files back for execution, the risk is minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 10:04 PM