brandkit-interview

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill conducts a series of questions to gather branding data and instructs the agent to save the results to a file named MARKE-ROH.md. This activity is entirely consistent with the skill's purpose as a brand identity generator.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided answers to generate a persistent document, which constitutes a standard data ingestion surface.
  • Ingestion points: User chat responses provided during the interactive interview process.
  • Boundary markers: None explicitly defined in the file-writing instructions.
  • Capability inventory: Local file writing (MARKE-ROH.md) to the current directory.
  • Sanitization: Not specified; user content is saved as a raw draft.
  • This represents a low-risk surface inherent to the skill's primary function of archiving user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 03:07 PM
Security Audit — agent-trust-hub — brandkit-interview