ClawHub
Back to skill

Security audit

Crypto Dca Reflection Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a bounded prompt-only reflection skill for crypto DCA planning and does not show file access, account access, trading automation, persistence, or hidden behavior.

Install only if you want reflective, non-automated help thinking through crypto DCA habits. It should not be treated as financial advice or connected to wallets, exchanges, or accounts without separate review.

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
99% confidence
Finding

The declared description is for a prompt-only financial reflection skill about dollar-cost averaging habits. The actual code chunk does not implement or demonstrate that behavior; instead, it tests a handler's security behavior when given a suspicious skill_name and verifies that no local file access occurs. This is a materially different primary purpose centered on filesystem safety/path traversal prevention, which is undeclared and unrelated to the stated reflection use case.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.