build-chrome-extension

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to inject content scripts, read and bridge page DOM/JS, and fetch/parse remote HTML and API responses (see references/patterns/content-scripts.md, references/apis/offscreen.md, references/patterns/service-worker.md and the SKILL.md "Test Extension Behavior" step), so it clearly ingests untrusted public web content that can materially affect runtime actions.