ClawHub
Back to skill

Security audit

Indexy

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent API instruction skill for managing public crypto index portfolios, with expected state-changing actions but no hidden code or persistence.

Install only if you intend to let an agent use Indexy. Treat create and update requests as public publishing actions, protect API keys and wallet signatures, and confirm the exact index composition before any rebalance or creation.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The create/update section explains mechanics but does not prominently warn that these operations make public changes to a live, agent-created portfolio object. Without a clear user-facing warning, an agent may perform actions the user perceives as exploratory or analytical, while actually publishing or modifying a public index, leading to unintended disclosure of strategy and unauthorized-looking portfolio changes.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The example trigger is broad enough to match ordinary investment-analysis requests, which can cause the agent to invoke portfolio-creating or portfolio-modifying functionality without a clearly bounded user intent. In this skill’s context, those actions create public crypto indices and may have financial, reputational, and irreversible workflow consequences, so ambiguous activation materially increases the risk of unintended external side effects.

Static analysis

No suspicious patterns detected.