chrome-devtools

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's examples and workflows embed plaintext credentials directly in scripts and CLI invocations (e.g., page.type('#password','secret'') and node fill.js --value "secret"), which would require the agent to insert real secrets verbatim into generated code/commands.

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

• Third-party content exposure detected (high risk: 1.00). The skill's scripts (e.g., navigate.js, aria-snapshot.js, snapshot.js, evaluate.js, console.js, network.js) explicitly navigate to and scrape arbitrary public URLs via the --url parameter and page.evaluate, and the SKILL.md workflow requires using those third‑party page snapshots/results (ARIA snapshots, DOM snapshots, network/console responses) to decide and drive subsequent interactions, so untrusted web content can materially influence tool actions.