rug-detection-checklist

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and analyze public on-chain and external user-generated sources (e.g., Solscan/Raydium holder and LP data, Twitter/Telegram posts, and project websites) as part of its workflow, exposing it to untrusted third-party content that could carry indirect prompt injection.