playwright-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill includes example automation code that embeds plaintext credentials (e.g., 'password123' in the login test), which would cause the LLM to output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow executes user-provided Playwright code that navigates to attacker-chosen pages/URIs (e.g., user supplies TARGET_URL and page.goto reads the resulting HTML/text at runtime), so outsider-authored free text can be ingested via the browser DOM.