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 explicitly fetches and ingests live data from public third‑party APIs (e.g., DefiLlama at https://bridges.llama.fi and protocol APIs like Wormhole, LayerZero, Across) as shown in SKILL.md/ARD.md and implemented in scripts/bridge_fetcher.py, protocol_adapters.py, and tx_tracker.py, and that external JSON is parsed and used to drive TVL rankings, route comparisons, and transaction-tracking decisions—meeting all criteria for exposure to untrusted third-party content.