ClawHub
Back to skill

Security audit

celebrity-hot-money-tag

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a Markdown knowledge prompt, but it gives direct copy-trading recommendations with unsupported win-rate claims and no visible risk disclosure.

Review this carefully before installing if users may rely on it for real trading. It should be treated as unverified market commentary, not personalized investment advice; users could lose money and should verify data independently or consult a licensed professional.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description explicitly offers investment recommendations and follow-trading advice but includes no warning that such guidance can cause financial loss or may be unsuitable for individual users. In a financial-analysis skill, presenting actionable trading advice without risk disclosure increases the chance users will treat it as reliable personalized guidance and act on it imprudently.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The repeated '推荐跟投' labels and quoted win rates create strong, action-oriented signals to mimic named traders, yet the skill provides no balancing disclosure about uncertainty, survivorship bias, stale data, market regime changes, or loss risk. Because the skill is specifically designed to influence trading decisions, the context makes this more dangerous than generic market commentary: users may interpret the recommendations as endorsement of copy-trading strategies.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.