better-auth-profile

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and ingests Markdown content from a recipe URL controlled by the skill provider.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching runtime instructions from an unverified third-party domain, resulting in a weak or unknown operational dependency classified as high.