ClawHub
Back to skill

Security audit

Crypto Fomo Cooldown

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only cooldown guide for crypto FOMO, with no evidence of file access, network calls, persistence, or hidden high-impact behavior.

Installers should understand this skill offers reflective decision support, not financial advice or market analysis. It appears low-risk from the inspected artifacts, but users should still make independent financial decisions and seek real support if trading feels compulsive or distressing.

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
96% confidence
Finding

The declared description is for a prompt-only behavioral guidance skill about crypto-investment FOMO. The actual code chunk does not implement or demonstrate that counseling behavior. Instead, it is a security-oriented test verifying that the handler resists local file access when given a suspicious skill name. That is a materially different purpose and capability from the declared mindset assistance. Even though the test asserts no file access occurs, the code is focused on filesystem access prevention and handler behavior, which is unrelated to the declared skill’s user-facing purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.