ClawHub
Back to skill

Security audit

Invest

Security checks for vulnerabilities and agentic risk

Overview

This skill provides educational investing guidance with clear disclaimers and no evidence of hidden code, credential access, persistence, or account-control behavior.

Use this as general investing education only. Do not rely on it for personalized recommendations, tax planning, estate planning, or decisions involving real money without checking current official sources and consulting a qualified 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The activation text includes broad phrases like "general investing questions" and "common investing concepts," which can overlap with many ordinary finance-related conversations without clearly defining boundaries. The file gives some redirect examples, but it does not provide a precise trigger list or negative examples that distinguish when the skill should not activate.

Static analysis

No suspicious patterns detected.