ClawHub
Back to skill

Security audit

HederaToolbox

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly transparent about using a paid Hedera MCP service, but its documented billing credential is only a public account ID, which creates a real authorization concern.

Review before installing. Use only a small prepaid balance unless the publisher documents stronger account-ownership verification or revocable credentials. Assume tool calls and query details are sent to HederaToolbox, and be careful with paid or on-chain write operations because they can consume your remote balance and create records through the platform account.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:138
Finding

Public Hedera Account ID Used as the Sole Billing Credential

Content
View full analysis
Remediation
View remediation

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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

MCP Endpoint

text
https://api.hederatoolbox.com/mcp

Standard MCP-over-HTTP. Compatible with any MCP client.

Static analysis

No suspicious patterns detected.