ClawHub
Back to skill

Security audit

Crypto Win Humility Check

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk prompt-only reflection skill for keeping perspective after an investment gain.

Installers should understand this is a reflection aid, not financial advice. The inspected artifacts do not show file access, account access, trading actions, or persistence.

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

Yes, there is a mismatch. The declared purpose describes a purely prompt-based reflective coaching skill for post-investment wins. The actual code chunk does not implement or demonstrate that reflective behavior; instead, it tests that the handler resists local file access when given a path-like skill name and returns a note about not using local files. That indicates the code’s primary concern is file-access/security behavior, not the stated reflective guidance purpose. While this may be a test rather than the full implementation, the supplied chunk's behavior is materially different from the declared description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.