playwright

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes literal plaintext credentials and a credit card number in code examples (e.g., 'SecurePassword123', '4111111111111111') and shows filling credentials directly into actions, which requires embedding secrets verbatim and is therefore an insecure pattern.

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 fetching and scraping arbitrary public websites (e.g., "Basic page navigation and scraping" and "Web Scraping: Extract Product Information" using page.goto(url), page.textContent()/$$eval(), and MCP tools like playwright_goto/playwright_execute_script), so untrusted third‑party page content is read and can directly influence automation actions and decisions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's MCP integration will run an external package at runtime via "npx -y @executeautomation/playwright-mcp-server" (executeautomation/playwright-mcp-server), which causes remote code to be fetched and executed and is listed as a required MCP server dependency, so it meets the criteria for a runtime-executed external dependency.