architecture-rendering

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts external image URLs in SKILL.md's "Sketch to Render" example (image_urls) and documents web search/web_search_citations in references/SSE-EVENTS.md, which shows it fetches and interprets arbitrary public web content that can influence generation and subsequent tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 07:56 AM