lista-loop

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and parse data from public Lista API endpoints (e.g., curl "https://api.lista.org/api/moolah/vault/list" and "https://api.lista.org/api/moolah/market/<MARKET_ID>"), and those external market/borrowRate responses are read and used to compute loop counts and recommendations, so untrusted third‑party content can materially influence decisions.