playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains examples and commands that pass secrets (e.g., passwords, session cookies) directly as CLI arguments (e.g., fill e2 "password123", cookie-set session_id abc123), which would require the LLM to embed secret values verbatim in generated commands/outputs and thus creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's CLI commands and examples (e.g., "playwright-cli open/goto https://example.com", the "scrape data from multiple pages" run-code example, and run-code/page.content/page.evaluate snippets in references/running-code.md) explicitly fetch and read arbitrary public web pages and use that content to drive interactions and generated test code, allowing untrusted third-party page content to influence subsequent actions.