ClawHub
Back to skill

Security audit

Crypto Exit Rule Drafter

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only crypto exit-rule drafting skill with no evidence of hidden file, wallet, network, or account access.

Before installing, understand that this skill may ask you to share crypto position details so it can draft exit rules. It does not appear to connect to exchanges, inspect wallets, fetch market data, or act on your behalf.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description says this is a prompt-only crypto exit-rule drafting skill with no special permissions. The actual code chunk does not implement or demonstrate drafting exit conditions at all; it is a security-focused test ensuring the handler does not read local files when passed a suspicious skill_name like '../../private-data'. That is a materially different primary purpose and behavior from the declared function, so this should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.