screenshot-to-code

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied screenshots to generate functional code, which creates a vulnerability to instructions embedded within the images.
  • Ingestion points: User-provided images are analyzed in the 'Analyze the Screenshot' section of SKILL.md.
  • Boundary markers: Absent. The instructions do not specify that the agent should ignore or treat text found within screenshots solely as design data.
  • Capability inventory: The skill is designed to generate complete, runnable code implementations in React, Vue, and HTML/CSS.
  • Sanitization: Absent. There are no instructions to sanitize textual content or validate the intent of text found within the UI designs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — screenshot-to-code