binance-tokenized-securities-info

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch and parse public Binance API endpoints (e.g., https://www.binance.com/bapi/defi/... for token lists, meta, market/status, dynamic data and K-line), which are untrusted third‑party web content that the agent reads and uses (e.g., reasonCode, marketStatus, dynamic token data) to decide actions, so it could enable indirect prompt injection.