ov-experience-memory

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

• Third-party content exposure detected (medium risk: 0.30). The workflow searches and reads the current user's Experience root via viking://user/memories/experiences/... and then ingests the contents of selected Experience files, which are user-authored within that tenant rather than trusted first-party provider content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to perform runtime reads of user Experience URIs such as viking://user/memories/experiences (and canonical viking://.../memories/experiences/...), which are fetched at runtime and can directly alter agent instructions and behavior.