playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's commands include examples that embed secrets verbatim (e.g., cookie-set session_id abc123, fill e2 "password123"), which instruct the agent to emit or copy plaintext credentials directly into CLI commands or page interactions.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to open/goto arbitrary external URLs (e.g., "playwright-cli open https://example.com", "playwright-cli goto https://playwright.dev") and to eval/snapshot page content, meaning it fetches and interprets untrusted public web pages whose content could alter subsequent actions.