playwriter

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows executing Playwright against arbitrary web pages (e.g., Core Workflow's page.goto('https://example.com')) and examples for "Read page content" (page.locator(...).innerText()) and network interception, so the agent can fetch and interpret untrusted public web content that could influence its actions.