playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that embed secrets verbatim (e.g., "password123", "abc123") and documents CLI commands (cookie-set, fill) that require placing secret values directly into generated commands, which creates an exfiltration risk.

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 playwright-cli open/goto/tab-new fetching arbitrary public web pages at runtime, whose DOM/text (and possibly console/dialog text) is then read into the agent’s LLM context through commands like snapshot, eval, and trace outputs.