ClawHub
Back to skill

Security audit

Intelligence

Security checks for vulnerabilities and agentic risk

Overview

This trading skill is mostly coherent, but it asks agents to deploy live strategies and send ambiguous wallet credential information to an external service without enough safety boundaries.

Review this carefully before installing. Only use it if you understand that it can guide live trading deployment through a third-party service; do not provide seed phrases, master private keys, or withdrawal-capable wallet credentials, and require a separate final confirmation before any live deployment or credential submission.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
references/workflow.md:71
Finding

Unsafe Transmission of Hyperliquid Wallet Credentials to an External Service

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description contains very broad trigger phrases such as "what's hot," "what's moving," and general single-pair drilldown requests, which can cause the agent to invoke this skill for a wide range of market-related prompts. Because the skill surfaces live ranked trading setups and recommended deploy templates, over-triggering can steer conversations into actionable financial guidance when a narrower informational tool might be more appropriate.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/workflow.md (reported line 29)May include surrounding context.

  • One sentence on the snapshot field(s) that drove the score
    • One AI Critic concern from buckets.md
  1. Ask which pair the user wants to dig into — do NOT auto-deploy.
text

If the user picks a pair → switch to Recipe B from step 1.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/workflow.md (reported line 111)May include surrounding context.

  • One sentence on the snapshot field(s) that drove the score
    • One AI Critic concern from buckets.md
  1. Ask which pair the user wants to dig into — do NOT auto-deploy.
text

If the user picks a pair → switch to Recipe B from step 1.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The workflow proceeds from deployment creation to posting wallet credentials for live trading without an explicit, mandatory user warning or confirmation that real funds may be used. In a trading skill, that omission is dangerous because it can normalize handing over sensitive wallet material and initiating live execution without a clear consent checkpoint tied to financial risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation explicitly instructs use of an authenticated external API via x-api-key but does not warn that requests leave the local environment or that credentials must be handled securely. In an agent-skill context, this omission can cause unreviewed transmission of secrets to a third-party service or unsafe logging/reuse of API keys, especially if downstream tooling auto-executes described calls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.