gate-info-addresstracker

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls external on-chain data tools (info_onchain_get_address_info, info_onchain_get_address_transactions, info_onchain_trace_fund_flow) and cites third‑party providers (BlockInfo / Nansen / Arkham in SKILL.md), ingesting public on-chain/label data which the LLM reads and uses to drive decisions (auto-upgrade to deep mode, tracing, and reporting), so untrusted third-party content can materially influence behavior.