ClawHub

Clawhub Krump Verify

Security checks across malware telemetry and agentic risk

Overview

The skill has a legitimate blockchain verification purpose, but it gives agents real payment and private-key-adjacent authority without clear safety boundaries.

Install only if you intentionally want an agent to help with Krump Verify on Story Aeneid. Use a dedicated low-balance wallet and dedicated relayer key, verify contract addresses and fees, and require manual approval for every token approval, deposit, x402 signature, receipt use, deployment, or contract transaction.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly encourages autonomous on-chain actions including token approvals, deposits, and payment flows, but it does not prominently require user consent, spending limits, or transaction review before funds are moved. In an agent context, this is dangerous because the skill normalizes agent-initiated spending and approvals, which can lead to unintended token transfers, excessive allowances, or misuse if an agent acts on ambiguous prompts or compromised downstream instructions.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The relayer section documents setting and operating with a private key (`RELAYER_PRIVATE_KEY`) without any accompanying guidance on secure secret storage, rotation, least privilege, or prohibition against exposing the key in prompts, logs, or client-side configuration. In a skill intended for agent use, this omission increases the risk that users or agents mishandle sensitive credentials, potentially leading to relayer compromise and unauthorized receipt submission or other privileged actions.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal