ClawHub
Back to skill

Security audit

Warden App

Security checks for vulnerabilities and agentic risk

Overview

This skill guides browser use of a crypto wallet app and includes clear confirmation safeguards for asset-moving actions.

Install only if you are comfortable letting an agent navigate a logged-in crypto wallet UI. Keep final signing or confirmation under your control, verify token, amount, chain, slippage, fees, leverage, and destination every time, and never provide seed phrases or private keys.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The notes instruct operators to execute swaps via natural-language chat prompts, but they do not pair that guidance with an explicit warning that this can move assets and requires careful human verification before any on-chain confirmation. In the context of an agentic wallet/browser automation skill, omission of a prominent confirmation warning increases the chance of accidental or misdirected transactions, especially if another agent uses this file as procedural guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.