pp-ollama-cloud

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

• Third-party content exposure detected (medium risk: 0.65). The skill is a CLI wrapper that can fetch live Ollama Cloud catalog data (e.g., via models, tags, advise/compare/budget which rely on live endpoints) and then returns that content as JSON/prose into the agent’s runtime context, which is outsider-authored free text from a public service.