ClawHub
Back to skill

Security audit

Crypto Budget Boundary Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-only crypto budgeting helper with no evidence of file access, account access, persistence, or hidden execution.

This appears suitable for users who want general budgeting boundaries for crypto, but it should be treated as educational guidance only and not as personalized regulated 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
  • 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
97% confidence
Finding

The declared purpose is a user-facing budgeting assistant for crypto allocation, but the code chunk does not implement or support budgeting behavior. Instead, it tests security-related handler behavior around preventing local file reads when given a suspicious skill name. This is a materially different primary purpose from conservative crypto spending guidance. While the test asserts that no file access should occur, the mismatch remains because the actual behavior is about file-access safety and handler validation, not budgeting or finance advice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.