gate-info-risk

General Rules

⚠️ STOP — You MUST read and strictly follow the shared runtime rules before proceeding. Do NOT select or call any tool until all rules are read. These rules have the highest priority. → Read gate-runtime-rules.md → Also read info-news-runtime-rules.md for gate-info and gate-news shared rules.

• Only call MCP tools explicitly listed in this skill. Tools not documented here must NOT be called, even if they exist in the MCP server.

CLI and playbook contract

1. Every CLI command MUST exist under gate-cli v0.5.2. This skill explicitly does NOT call info compliance check-address-risk (not shipped); address risk comes from info onchain get-address-info.
2. Call gate-cli info … / gate-cli news … only as listed in playbooks/gate-info-risk.yaml. When preflight route is CLI, do not call Gate MCP tools from this skill.
3. Missing data NEVER counts as "low risk". When the primary command for a chosen playbook is unavailable, the verdict is UNABLE_TO_ASSESS (scope limited; localized labels may appear in the user report) plus an explicit retry hint.
4. Always pass --format json. Required slots (token+chain, address+chain, symbol) must be present; if ambiguous, ask the user.
5. The report is safety-first: the verdict line comes BEFORE evidence, and high-severity items are always surfaced before medium or low.
6. No buy / sell advice. No price predictions. Use verdict bands HIGH / MEDIUM / LOW / UNABLE_TO_ASSESS in this skill’s logic; the final user report may localize those labels. Always include a “what to verify next” list.