ClawHub
Back to skill

Security audit

Stock Market

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent stock-analysis planning skill that stores confirmed preferences locally and does not include hidden execution, broker access, or data exfiltration behavior.

Before installing, decide whether you want automatic activation or explicit-only use. The skill may store local trading preferences, risk limits, watchlists, and review notes under ~/stock-market/, so only approve memory entries you are comfortable keeping there. It does not place trades or connect brokers automatically.

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 skill allows automatic activation whenever the user discusses stock market analysis, watchlists, or trade planning, which are broad conversational triggers that can easily match ordinary discussion rather than an explicit request to use the skill. This can cause the agent to engage specialized behavior and begin collecting sensitive preference or risk information without sufficiently clear user intent, increasing the chance of overreach or unexpected persistence.

Static analysis

No suspicious patterns detected.