playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes commands that embed secret-like values verbatim (e.g., cookie-set session_id abc123), and the CLI usage would require the agent to output or include secret values directly in commands/requests.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly opens and navigates arbitrary public URLs and scrapes or executes page content (see commands like "open/goto" and the "run-code" scraping examples in references/running-code.md and the concurrent scraping example in references/session-management.md), so untrusted third-party webpages can be ingested and influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill repeatedly runs "npx --yes @playwright/cli@latest" at runtime, which fetches and executes the @playwright/cli package from the npm registry (e.g., https://registry.npmjs.org/@playwright/cli), so an external package is fetched-and-run and is required for the skill to operate.