monitoring-cross-chain-bridges

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

• Third-party content exposure detected (high risk: 0.80). The skill actively fetches and ingests data from public third-party APIs (e.g., DefiLlama Bridges at https://bridges.llama.fi in scripts/bridge_fetcher.py and protocol APIs like Wormhole/LayerZero/Across in protocol_adapters.py and tx_tracker.py) which the agent reads and uses to drive comparisons, transaction-tracking, and routing decisions, so untrusted external content can materially influence its actions.