image-to-code

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts to determine the visual direction and technical implementation of generated websites.
  • Ingestion points: User-provided strings (e.g., "clean", "crazy creative", "premium SaaS") are used to adapt baseline configurations such as DESIGN_VARIANCE and ART_DIRECTION in SKILL.md.
  • Boundary markers: The instructions do not define explicit delimiters or "ignore embedded instructions" warnings to isolate user data from the agent's core instructions.
  • Capability inventory: The agent uses image generation tools and writes implementation code for frontend websites based on the processed inputs (SKILL.md).
  • Sanitization: There is no evidence of sanitization, escaping, or validation logic applied to the user-provided inputs within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 09:16 PM