chrome-devtools

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed plaintext passwords and CLI values (e.g., await page.type('#password', 'secret') and --value "secret"), and shows passing secrets as command-line arguments, which requires the agent to include secret values verbatim and is therefore high-risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates to and scrapes arbitrary public web pages (e.g., navigate.js, aria-snapshot.js, snapshot.js, network.js, evaluate.js) and then uses the extracted content/ARIA refs to drive interactions (select-ref.js, click.js, fill.js), so untrusted third-party page content can directly influence the agent's actions.