longbridge-onchain

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

• Third-party content exposure detected (high risk: 0.90). The skill's Workflow and Data scope explicitly instruct the agent to accept and interpret on-chain data "provided" or "pasted" by the user or sourced from public third-party sites (Glassnode, Dune Analytics, Nansen, DefiLlama), so it will ingest untrusted external/web-origin content and use it to drive analysis and verdicts.