google-ads-api-quickstart

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

• Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to fetch release notes and client library documentation from external URLs using web search or URL-reading tools at runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to dynamically fetch release notes and documentation URLs at runtime to resolve API and library versions, constituting an unverifiable runtime external dependency.