playwright-skill

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and README explicitly include Playwright CLI/browser-automation guides (playwright-cli SKILL.md and linked pages like "advanced-workflows", "running-custom-code", and "test-generation") that describe scraping/navigating arbitrary web pages and global-setup examples that fetch a configurable baseURL, so the agent workflow clearly ingests untrusted public web content which could influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill's CI and container examples fetch and execute remote artifacts at runtime (notably the Playwright container image mcr.microsoft.com/playwright:v1.52.0-noble and GitHub Action usages such as actions/checkout@v4, actions/setup-node@v4, actions/upload-artifact@v4, etc.), which are external dependencies that run remote code in CI jobs.