ClawHub
Back to skill

Security audit

HashPack Wallet

Security checks for vulnerabilities and agentic risk

Overview

The skill is a small HashPack/Hedera integration guide, but it includes fund-moving transaction signing examples without clear user-consent or safety guidance.

Review this skill carefully before installation. It appears to be a simple integration reference, not malware, but any agent using it should add mandatory transaction review and explicit user approval before signing or submitting Hedera transactions, especially on mainnet.

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

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly demonstrates transaction signing for Hedera transfers and describes state-changing transaction types, but it provides no warning that these operations can move funds, mutate on-chain state, or require careful user confirmation. In an agent-skill context, omission of such warnings increases the risk that an integrator or downstream agent will treat signing as routine, potentially leading to unintended financial actions or unsafe automation.

Static analysis

No suspicious patterns detected.