design-skill

Warn

Audited by Snyk on Mar 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md's "External Content And Scraping" section explicitly instructs the agent to accept a user-provided URL and system-supplied page content/screenshot and to clone/derive layout and code from that scraped HTML/screenshots, which means the agent will ingest and act on arbitrary public web content (open third‑party pages) that could contain untrusted instructions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 04:26 AM
Issues
1