playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The doc includes examples that embed secrets (cookie values and a password) directly in CLI arguments, which would require the LLM to reproduce those secret values verbatim when generating commands or examples.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md describes a browser automation workflow (e.g., playwright-cli goto/open and subsequent snapshot/eval) that will cause the agent to ingest page-derived text/DOM state from outsider-controlled web content at runtime into the LLM context.