prototype-design

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external requirement documents.
  • Ingestion points: Reads design requirements from 'output/doc/requirements-analysis-review.md' and user-provided files (SKILL.md).
  • Boundary markers: No specific delimiters or instructions are used to isolate untrusted data from the system prompt.
  • Capability inventory: The skill writes multiple files (HTML, TXT, MD) to the 'output/design-output' directory (SKILL.md).
  • Sanitization: There is no evidence of input validation or sanitization for the ingested requirement text.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:35 PM