functions

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

• Third-party content exposure detected (high risk: 0.90). The skill's examples and function code explicitly navigate to and scrape arbitrary external URLs provided via params.url (e.g., "await page.goto(params.url)" and the test/example calling "https://news.ycombinator.com"), so it ingests untrusted public web content that can influence execution.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime API calls to https://api.browserbase.com/v1/functions/... (e.g., the /invoke and /invocations endpoints) which trigger execution of deployed function code on Browserbase and are required for the skill to operate, so this external URL executes remote code at runtime.