anycap-worldcup-predict

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses anycap search --prompt / anycap search --query to retrieve player/squad data from public web sources, and that retrieved free-text content is then placed into the agent’s LLM context (indirect prompt injection risk via untrusted web text).