Back to skill

Security audit

Hyperliquid Us Stock Perps

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because scanners reported no clear malicious behavior, while noting a possible privacy concern about sending user input to an external service; coverage was partial, so the evidence is incomplete.

The verdict is benign with medium confidence, not a guarantee of safety. Before installing, consider whether you are comfortable with your input being sent to an external service, and avoid sharing confidential financial or account information. The scan was partial because the manifest could not be parsed, so some evidence is incomplete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends the user's input to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill instructs the agent to create a Finch/Maneki AI task containing the user's input. Although it identifies the services involved, it does not warn the user that their question will be shared externally and could include sensitive financial information.

Content

No source excerpt is available for this finding.