four-meme

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to web-fetch and parse the public four.meme site (https://four.meme) in the "Data Sources" and "Workflow" sections to extract token listings/contract addresses that are then used to drive on-chain reads and follow-up actions, exposing it to untrusted third-party content that could carry indirect prompt-injection.