liquidation-cascade-monitor

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 data from public third‑party APIs (e.g., DeFiLlama: https://api.llama.fi/protocols and https://api.llama.fi/v2/protocols/{protocol}/liquidations) and directly uses that untrusted external data in its workflow to compute cascade impacts and trading recommendations (see the Data Collection / Pre-flight steps in SKILL.md), so third‑party content can materially influence agent decisions.