ui-cloner-brand-interview

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: User answers provided during the brand interview phase (SKILL.md).
  • Boundary markers: The skill does not use delimiters or safety instructions to wrap user input or warn the agent to ignore embedded commands.
  • Capability inventory: The skill possesses the capability to write user data to 'plans/02-brand-interview.md' and trigger subsequent processing via 'ui-cloner-synthesis' (SKILL.md).
  • Sanitization: There is no evidence of input validation, filtering, or escaping of the user-provided text before it is recorded.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:19 AM