playwright

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill's CLI examples and form-fill commands embed plaintext credentials (e.g., fill e2 "password123"), which implies the agent may ask for and emit real secret values verbatim in generated commands, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow is to run the Playwright CLI against user-specified URLs/pages (e.g., pwcli open https://...), which causes the browser to fetch and ingest outsider-authored web page text into the LLM context via the CLI’s snapshot/element-ref extraction.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The wrapper script runs npx to fetch and execute the remote npm package @playwright/cli at runtime (via "npx --yes --package @playwright/cli playwright-cli"), which downloads and executes remote code as a required dependency.