Back to skill

Security audit

HyperGrok Hyperliquid Account

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because scanners report read-only account data retrieval with no trading or account changes, while noting extra account metadata queries; confidence is medium and coverage is incomplete.

The verdict is benign, but consider whether you want the skill to retrieve account roles and authorized-agent details as well as financial data. Skillspector coverage is marked partial because two local references could not be resolved, so the 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The portfolio, userFees, and userRateLimit queries match the description. However, querying account roles and enumerating authorized agents are additional account-access metadata capabilities not disclosed in the declared purpose. They are explicit data retrievals rather than implementation details needed for the stated financial queries. No trading, account modification, or other write behavior is shown.

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 · SKILL.md (reported line 19)May include surrounding context.

bash
ADDR=$HYPERLIQUID_ACCOUNT_ADDRESS
BASE=$([ "$HYPERLIQUID_NETWORK" = mainnet ] && echo https://api.hyperliquid.xyz || echo https://api.hyperliquid-testnet.xyz)
hl() { curl -sS -m 15 -X POST "$BASE/info" -H 'Content-Type: application/json' -d "$1"; }
python