playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt shows commands that read and emit secrets (cookie-get/cookie-set, raw output assigned to TOKEN) and contains plaintext example passwords (e.g., "password123"/"abc123"), so an agent following it may need to handle and output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can be ingested via runtime browser content: playwright-cli goto/open/tab-new loads arbitrary public web pages, and subsequent snapshot/eval/trace outputs include DOM text (and potentially console/network response bodies) from that page into the agent’s LLM context.