ClawHub
Back to skill

Security audit

Openclast Wallet

Security checks for vulnerabilities and agentic risk

Overview

This wallet skill is high-impact because it can guide transactions, but its behavior is disclosed, purpose-aligned, and defaults to explicit approval.

Install only if you intend to let an agent help operate a crypto wallet. Keep the default notify/approval mode unless you deliberately want automated sends, set strict per-transaction and daily limits, restrict recipients and chains, and avoid exporting private keys unless absolutely necessary.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · SKILL.md (reported line 65)May include surrounding context.

md
## Config rules (apply when present)

- `wallets.defaults.spending.mode`: `"notify"` (default) or `"auto"` (sends without approval).
- `wallets.defaults.spending.limitPerTx`, `dailyLimit`, `allowedChains`, `allowedRecipients`, `notifyChannels`: enforced for send/ERC20/contract calls.
- `wallets.notify.primaryChannel`: where pending approvals are notified.
- `wallets.interactWithUnverifiedContracts`: if `false`, only allow `verifiedTokenAddresses` and `verifiedContractAddresses`.

Static analysis

No suspicious patterns detected.