ClawHub
Back to skill

Security audit

gate-info-marketoverview

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only crypto market overview helper that uses disclosed Gate MCP data tools and does not request credentials, local file access, persistence, or mutation authority.

Install only if you use the Gate Info MCP server and want market-wide crypto summaries. Review outputs as informational market data, not investment advice, and use a more specific skill for coin analysis, technical analysis, contract risk, or news-only requests.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • 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, routing, and graceful fallback behavior).
- **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
89% confidence
Finding

The trigger phrases are very broad generic market-language terms, which can cause the skill to activate for loosely related financial discussion rather than only the narrow intended use case. In a routing system, this can misclassify user intent and divert requests away from a more appropriate skill, reducing reliability and potentially causing incomplete or misleading responses.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Mandating Chinese output at the scenario level without checking user preference creates a policy and usability issue: the system may respond in a language the user did not request or no longer prefers. While not a direct code-execution or data-exfiltration flaw, it can cause incorrect behavior, undermine trust, and increase the chance of unsafe misunderstanding in financial contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The Chinese scenario examples are ambiguous and do not clearly separate language preference from functional scope, so the skill may trigger on generic phrasing without confirming that the user wants a crypto-wide overview. This increases the chance of incorrect activation in multilingual environments and can lead to wrong-skill routing or responses that do not match user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.