ai-pixel-perfect-design-generator

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @aipixelperfect/client package via NPM and the aipixelperfect-sdk package via Pip. These packages originate from sources that are not recognized as trusted organizations or part of the specific vendor's infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text prompts from users and interpolates them into API requests for image synthesis and refinement.
  • Ingestion points: User-provided prompt input in the JavaScript, Python, and HTML implementation examples within SKILL.md.
  • Boundary markers: Absent; user input is passed directly into the synthesize and refine API calls without delimiters or explicit instructions to ignore embedded instructions.
  • Capability inventory: The skill performs network operations via fetch and client SDKs to api.aipixelperfect.com and abnormal-codex.github.io.
  • Sanitization: No evidence of input sanitization, validation, or escaping before transmission to the remote service.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 03:58 AM