ClawHub
Back to skill

Security audit

OpenDEX Solana Token API

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it documents wallet-linked API actions that can change OpenDex watchlists without authentication and does not clearly warn users about wallet privacy exposure.

Review this before installing if you plan to let an agent use your wallet address. Prefer using it only for read-only token lookups unless you explicitly approve wallet-linked actions, and avoid using other people’s wallet addresses for watchlist or sentiment changes.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
#### Remove from Watchlist
```
DELETE /api/watchlist
Content-Type: application/json

{ "wallet": "<WALLET>", "mint": "<MINT>" }
Confidence
93% confidence
Finding
The documented watchlist deletion operation takes a raw `wallet` and `mint` in the request body and is marked as unauthenticated, which implies an agent or caller could request modifications to another user's watchlist by supplying an arbitrary wallet address. In skill context, this is more dangerous because the document presents the endpoint as normal usage without any ownership verification, enabling unauthorized state-changing actions if the backend behaves as documented.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill instructs users to obtain keys through a web UI by connecting their wallet, which implies sharing wallet information with an external service. Although the file documents authentication mechanics, it does not clearly warn users that wallet addresses and related request metadata will be sent to third-party endpoints.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill documents multiple endpoints that send wallet identifiers for sentiment, watchlist, vote checks, and submission workflows without clearly warning that wallet addresses may be personal identifiers or linkable activity data. An agent using this skill could transmit a user's wallet to a third-party service without sufficient user awareness, creating privacy leakage and correlation risk across actions.

Static analysis

No suspicious patterns detected.