ClawHub
Back to skill

Security audit

Robonet

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Robonet trading integration, but it documents live leveraged deployment without clear risk warnings or an explicit confirmation gate.

Review this carefully before installing. It appears to be a legitimate trading-workbench skill, not malware, but live deployment tools can affect real funds. Only use deployment_create or deployment_start after explicitly confirming the account, symbol, leverage, wallet or vault, capital at risk, and that you accept possible losses, fees, liquidation, and ongoing remote trading until stopped.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly documents live deployment to Hyperliquid and even recommends deployment after positive backtests, but it does not place a clear, proximate warning that these actions can trigger real-money trading, losses, leverage exposure, and account impact. In a trading skill, omission of an explicit risk/consent warning materially increases the chance that a user or downstream agent will treat deployment as a routine operational step rather than a high-risk financial action.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The deployment example is written as a direct executable-style prompt to deploy a strategy live with leverage, without any warning that this may initiate real-money trading. This is especially dangerous because examples strongly shape agent behavior, and a user or assistant may copy the prompt verbatim into an execution flow that commits capital immediately.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The deployment section documents tools that can create, start, and stop live trading agents on a real exchange, but it does not prominently warn that these actions can cause real financial loss, market exposure, or changes to live systems. In an agent setting, this omission increases the chance that a model or user treats deployment as a routine low-risk action, leading to unintended live trades or operational changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.