Back to skill

Security audit

Hyperliquid Plan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Hyperliquid trade-planning aid that produces unsigned tickets and explicitly avoids signing, submitting, or handling private keys.

Before using this skill, be aware that it may use your public Hyperliquid account or subaccount address to read positions, orders, balances, fees, and market data for planning. Do not provide private keys or signer secrets to this skill, and review any optional `npx skills add` installation command before running it because it is not version-pinned.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
ces.md); mark inapplicable entry-sizing fields as such with a reason. Use `node scripts/risk.mjs --help` for deterministic arithmetic. The stop fill must includ

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The documentation instructs use of npx skills add ... without pinning an exact package version or integrity, which can cause installation of whatever version is current at execution time. If the package or one of its dependencies is compromised, users may run attacker-controlled code during install, and the skill context makes this more concerning because it relates to crypto/DeFi workflows where downstream compromise could affect sensitive operational environments.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/official-tools.md (reported line 30)May include surrounding context.

For HTTP-capable harnesses, use the official Info endpoint directly for reads. The equivalent metadata request is:

sh
curl --fail-with-body https://api.hyperliquid.xyz/info \
  -H 'Content-Type: application/json' \
  --data '{"type":"meta"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/official-tools.md (reported line 30)May include surrounding context.

For HTTP-capable harnesses, use the official Info endpoint directly for reads. The equivalent metadata request is:

sh
curl --fail-with-body https://api.hyperliquid.xyz/info \
  -H 'Content-Type: application/json' \
  --data '{"type":"meta"}'

Static analysis

No suspicious patterns detected.