ClawHub
Back to skill

Security audit

Family Crypto Explainer

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only conversation helper with no evidence of hidden access, persistence, or data collection.

Install only if you want a lightweight prompt guide for family crypto conversations. It does not appear to inspect wallets or accounts, but it also does not provide specialized financial, legal, or scam-forensics capability beyond conversational framing.

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 purpose describes a conversational, prompt-only explanation aid for discussing crypto with non-crypto family members. The actual code chunk does not implement or demonstrate that functionality. Instead, it tests security-related behavior: ensuring the handler does not open local files when given a suspicious skill_name resembling a path traversal attempt. This is materially different from the stated primary purpose and concerns undeclared resource-handling/security behavior rather than plain-language crypto guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.