ClawHub
Back to skill

Security audit

gate-info-defianalysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only DeFi data reporter with some broad query routing, but no hidden install, credential use, persistence, or mutation behavior was found.

Install this only if you want read-only DeFi market analysis through Gate Info MCP. For generic yield or finance questions, ask the agent to clarify whether you mean DeFi before using the skill, and treat APY, reserve, and liquidation outputs as informational rather than financial advice.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

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.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
## 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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The routing table uses broad trigger phrases like "best yield" and "where to earn," which are common financial queries and may cause this DeFi-focused skill to activate for requests that are not clearly within its intended scope. Over-broad activation can misroute users, apply the wrong safety framing, and surface DeFi-specific guidance in contexts where a narrower or safer skill should have been used.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The decision logic says ambiguous intent should either ask one clarifying question or default to Overview, which permits execution without confirming that the request is actually DeFi-specific. This increases the chance of unintended tool use and incorrect routing, especially for mixed or underspecified user requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The safety rules state that the skill is intended only for users aged 18 or above with full civil capacity in their jurisdiction. This introduces a blanket policy constraint in natural-language instructions that is not presented as a user-selectable option or justified as a documented regional compliance requirement within this file.

Content

No source excerpt is available for this finding.