Security audit
Security checks for vulnerabilities and agentic risk
This skill is a read-only cryptocurrency comparison helper that uses disclosed Gate Info MCP tools and does not request credentials, persistence, or local file authority.
Install only if you want an agent to query Gate Info market and coin data for crypto comparisons. Review outputs as informational analysis, not investment advice, and expect the skill to ask for clarification when coin symbols or project names are ambiguous.
The trigger phrases include very broad natural-language terms such as "compare," "vs," "which is better," and "difference," which can match many ordinary conversations that are not actually requests for this coin-comparison workflow. This can cause the skill to activate in unintended contexts, leading to unnecessary tool calls, incorrect routing, or disclosure of analysis the user did not request.
Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
## 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 `./references/gate-runtime-rules.md`
→ Also read `./references/info-news-runtime-rules.md` for gate-info / gate-news shared rules (tool degradation, report standards, security, and output standards).
- **Only call MCP tools explicitly listed in this skill.** Tools not documented here must NOT be called, even if they
The trigger scenario description is underspecified and lacks strong exclusion rules, so requests like broad sector questions or vague asset mentions may still be routed into this workflow. In practice this increases the chance of misclassification, spurious tool usage, and user confusion, especially because the skill can fan out into multiple parallel calls per invocation.