accessibility-audit

Warn

Audited by Snyk on Feb 21, 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's SKILL.md explicitly supports scanning arbitrary URLs (Audit Scope "a URL") and instructs the agent to navigate to the user-provided site via mcp__playwright__browser_navigate, ingest the page (title, accessibility tree, screenshots, console messages) and base audit actions on that content, which exposes the agent to untrusted third-party webpages that could supply instructions or data influencing subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 06:05 AM