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 embed plaintext secrets (e.g., cookie-set session_id abc123, fill e2 "password123") and instruct constructing CLI commands that would require the LLM to include secret values verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can be ingested via runtime browser content: playwright-cli goto/open loads arbitrary public web pages, and the skill’s required “snapshot after each command” produces LLM-readable DOM/text (e.g., page titles/element text) that is then fed into the agent context.