NYC

devops

Warn

Audited by Snyk on Feb 16, 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 includes browser-rendering and crawler examples that navigate arbitrary external URLs and scrape page content (e.g., references/browser-rendering.md and references/cloudflare-workers-advanced.md show page.goto('https://news.ycombinator.com') and page.goto(url) where url comes from request params or queue messages, and an AI-powered scraper that passes scraped HTML to an LLM), which clearly ingests untrusted third‑party/web content for the agent to read and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:30 AM