ov-resources

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can be ingested when the required workflow uses ov add-resource with a runtime-provided URL/source (e.g., https://... or a ZIP/Git repo), which downloads/parses external content into viking://resources/ and then feeds it into the agent’s LLM context via subsequent resource reading/search/semantic processing.