ClawHub
Back to skill

Security audit

Today's Orders

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Solana trading-planning skill that discloses wallet review and trade preview behavior, with execution gated on user approval.

Install only if you are comfortable with an agent reading a Solana wallet address and preparing trading guidance through OKX OnchainOS. Treat the approved order as financial decision support, verify quotes and routes yourself, and do not approve broadcast unless you intend to execute the transaction.

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest advertises sensitive financial behavior—reading a Solana wallet, approving an onchain order, and generating a forbidden order—without any user-facing warning that these actions may affect assets, strategy, or transaction decisions. In an onchain trading context, missing warnings and consent cues can mislead users about the significance of the skill and increase the risk of unauthorized or poorly understood financial actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-requires Chinese section labels in its fixed output without offering a language preference or opt-in path. This can create accessibility and usability issues, increase the chance of user misunderstanding, and lead downstream systems or operators to misread safety-critical trading instructions or execution status.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill enables implicit invocation for a workflow that can read a wallet and influence onchain order approval, but it defines no trigger constraints, exclusions, or explicit confirmation boundaries. In a financial/onchain context, automatic invocation increases the chance the agent activates during ambiguous user requests and initiates sensitive trading-related actions without sufficiently deliberate user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.