ClawHub
Back to skill

Security audit

HyperGrok Desk Monitoring

Security checks for vulnerabilities and agentic risk

Overview

This skill gives read-only trading-desk monitoring guidance and clearly forbids placing or changing orders, though users should confirm any persistent watches before starting them.

Before installing, understand that this skill is intended for trading-desk monitoring and may lead your agent to start read-only watches or scheduled checks that log market/account state. Confirm the market, account scope, schedule, alert destination, and stop condition before creating any persistent watch.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase "watch X" is overly broad and can match many ordinary user requests, causing the skill to activate outside its intended scope. In this skill's context, that matters because activation can start monitoring routines, file writes, logging, or scheduled checks, which increases the chance of unintended behavior or confusing agent routing even though the skill is nominally read-only.

Content

No source excerpt is available for this finding.