testing-mastery

Warn

Audited by Snyk on Mar 1, 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). This skill explicitly navigates to arbitrary public URLs via scripts/playwright_runner.py (referenced in SKILL.md under Runtime Scripts) and programmatically reads/interprets page content (title, headings, console errors, evaluates JS, element counts) which exposes the agent to untrusted third-party web content that could influence tool outputs or next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:27 PM