ClawHub
Back to skill

Security audit

HyperGrok Desk Post Trade Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed trading-desk journaling and review procedure with no hidden code, install behavior, or unrelated authority.

Before installing, confirm you want the agent to read trading records and write journal/review files for the desk. The skill may also send review summaries by DM to the Desk Lead and user as part of its stated workflow.

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 description says to use the skill "after any send" and when the user asks "how did that go," which are broad phrases that can overlap with common conversation and multiple desk actions. The trigger scope is not narrowly constrained with explicit exclusions or negative examples, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.