design-md

Warn

Audited by Snyk on Feb 27, 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's Retrieval & Networking steps explicitly instruct the agent to download and parse user-provided HTML and screenshots from the project's htmlCode.downloadUrl and screenshot.downloadUrl (using web_fetch/read_url_content) from Stitch project assets, which are untrusted third-party/user-generated content that the agent must read and use to make design decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 11:47 PM