ClawHub
Back to skill

Security audit

Crypto Research

Security checks for vulnerabilities and agentic risk

Overview

This skill uses CoinMarketCap tools for cryptocurrency research and does not include hidden code, persistence, or unrelated access.

Install this if you are comfortable using CoinMarketCap MCP for crypto research. Token names or symbols you ask about will be sent to CoinMarketCap, and any API key should be managed carefully. Treat the output as research support, not 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrases are broad enough to match common conversational crypto questions such as 'tell me about [coin]' or 'should I invest in [coin]'. That can cause the skill to activate more often than users expect, increasing unintended external data access and making it easier for the agent to route sensitive or casual queries into this workflow without clear consent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to call CoinMarketCap-backed MCP tools but does not warn users that their token query will be sent to an external service. This creates a transparency and privacy issue because users may assume analysis is local, while their requests and potentially sensitive investment interests are disclosed to a third party.

Static analysis

No suspicious patterns detected.