ollama-setup

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

• Third-party content exposure detected (high risk: 0.70). The skill's Step 2 explicitly scrapes model names from the public site https://ollama.com/search?c=cloud (via curl/grep/sed) and uses those fetched model names to populate choices that the agent will test and then launch/save, so untrusted third-party content can influence tool use.