Security audit
Security checks for vulnerabilities and agentic risk
This skill is a read-only cryptocurrency comparison helper whose requested tools and behavior match its stated purpose.
Before installing, confirm you have or want the Gate Info MCP integration. The skill should only retrieve public crypto market, project, ranking, and technical data for comparisons, and its output should be treated as informational rather than investment advice.
The skill description embeds very broad trigger phrases such as 'compare', 'vs', and 'which is better', which can match many ordinary requests outside the intended coin-comparison scope. In an agentic environment, this can cause incorrect skill activation and unintended tool use, leading to over-collection of data, wrong routing, or confusing outputs.
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 section states broad examples but does not define strong boundaries for when the skill should or should not activate. This ambiguity increases the chance of accidental invocation, especially when user text mentions multiple assets or sectors in a non-comparison context.
No suspicious patterns detected.