playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows examples that embed secrets verbatim in CLI commands (e.g., cookie-set with a token and fill with a plaintext password) which would require the LLM/agent to handle or reproduce secret values directly.

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

• Third-party content exposure detected (medium risk: 0.30). Skill runtime path: the required workflow uses Playwright to ingest and execute arbitrary eval/element text from the loaded page DOM (e.g., playwright-cli eval "el => el.textContent" and playwright-cli snapshot), so outsider-authored free text can be loaded from attacker-controlled webpages into the agent’s browser context.