ai-sdk

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches documentation via search results and selected URLs from ai-sdk.dev, which represents outsider-searchable external content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references remote documentation and search endpoints on ai-sdk.dev to fetch instructions and runtime guidance, representing a weak or unknown third-party operational dependency.