reviewing-a11y

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 instructs the orchestrator to fetch and analyze live, user-provided URLs and Figma links using Playwright (mcp__playwright__browser_navigate / snapshot) and WebFetch as part of its required workflow (see SKILL.md / SKILL.ja.md and references/page-review.md and references/design-review.md), so it ingests arbitrary public third‑party content that can materially influence tool use and decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 06:51 AM