ClawHub
Back to skill

Security audit

Hyperliquid US Stock Perps (Maneki via Finch)

Security checks for vulnerabilities and agentic risk

Overview

The skill provides market analysis through disclosed external services and requires explicit approval for paid runs.

Your ticker and question will be sent to Finch and Maneki AI. Avoid including private account details or confidential trading information. Paid runs require your explicit approval. Review the connection instructions before adding the MCP server; that external guide was unavailable during this review.

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
  • 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 a third-party service without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill instructs the agent to create a Finch task containing the user's input for Maneki AI. Although it names the services, it does not instruct the agent to notify the user that their ticker and question will be shared externally before submitting them.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.