Back to skill

Security audit

Vault Intelligence

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed Paradex vault analysis and recommendations using Paradex vault data, with no code execution, persistence, or hidden data handling found.

Use this as an analytics aid, not as investment advice. Before acting on any vault recommendation, independently verify current vault data, withdrawal lockups, operator risk, liquidity, and whether the risk profile matches your own financial situation.

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
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
97% confidence
Finding

The trigger guidance is overly broad because it activates on generic financial terms like "yield," "earn," and "passive" whenever the system infers a Paradex context. This can cause unintended invocation of the skill for loosely related requests, leading the agent to surface vault recommendations or analytics when the user did not explicitly ask for vault analysis, increasing the chance of irrelevant financial guidance and mistaken tool use.

Content

No source excerpt is available for this finding.