playwright

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill's CLI examples and form-fill commands embed plaintext credentials (e.g., fill e2 "password123"), which implies the agent may ask for and emit real secret values verbatim in generated commands, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow runs npx --package @playwright/cli playwright-cli (Playwright CLI) which fetches and renders user-specified web pages/URLs; the resulting page text/DOM-derived content is then ingested into the agent context via the CLI’s snapshot/element-ref outputs, making it an outsider source (public web content at runtime).

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

• Potentially malicious external URL detected (high risk: 1.00). The wrapper script (scripts/playwright_cli.sh) runs npx --package @playwright/cli playwright-cli at runtime, which fetches and executes remote code from the npm registry (e.g., registry.npmjs.org for @playwright/cli), so the skill relies on downloading and running external code.