playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples and commands that pass sensitive values (passwords, session cookies, tokens) directly as command-line arguments or fill inputs (e.g., cookie-set session_id abc123, fill e2 "password123", curl examples with tokens), which would force the LLM to handle or emit secret values verbatim in generated commands or code.

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

• Third-party content exposure detected (high risk: 0.85). High: the required runtime workflow uses playwright-cli goto/open to fetch arbitrary web pages (public web content) and then ingests their readable DOM text into the agent via playwright-cli snapshot/--raw snapshot outputs and subsequent eval/locator generation.