playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes explicit CLI examples that embed plaintext credentials (e.g., playwright-cli fill e2 "password123"), which would require the LLM to handle or emit secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). playwright-cli’s required workflow ingests free text from first-party browser DOM/snapshots and page/network contents produced after the user navigates to a page (via goto/open, snapshot, eval, tracing/network), so outsider-authored content from arbitrary webpages can become LLM-readable.