ClawHub
Back to skill

Security audit

Utxo

Security checks for vulnerabilities and agentic risk

Overview

The skill appears operationally simple and non-destructive, but it is presented as a UTXO/blockchain reference while mostly providing generic finance and checklist text.

Treat this as a review item before installing. The script itself looks low-risk because it only prints static text, but users should not rely on it for actual UTXO, blockchain, compliance, or financial decisions unless the publisher replaces the placeholder content with accurate, scoped material or renames the skill to match what it really provides.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill advertises itself as a UTXO/blockchain reference tool, but the documented commands are largely generic finance, compliance, risk, and strategy topics with no concrete UTXO-specific functionality. This is dangerous because users may trust the skill for blockchain-specific guidance and receive irrelevant or misleading information, which can lead to faulty operational or compliance decisions in financial contexts.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation presents the skill as blockchain/UTXO-oriented, but the command set centers on broad reference categories like regulations, risks, instruments, and strategies rather than UTXO mechanics. In a security-sensitive domain such as blockchain and finance, this mismatch can cause users or agents to apply the tool in inappropriate contexts and rely on incomplete or non-specialized guidance.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The top comment asserts a specific intent: a UTXO reference tool for blockchain work. However, the command outputs include generic formulas, compliance, risk, instrument, and inspection checklist text, and even define 'Utxo' as 'the primary subject of this reference' without substantive blockchain detail, which contradicts the apparent documentation intent rather than merely omitting detail.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The command set claims to provide UTXO reference topics, but commands like formulas, regulations, risks, instruments, strategies, and checklist expose broad domain-agnostic content that is not meaningfully tied to UTXO concepts. This is a semantic mismatch between the stated purpose of a blockchain UTXO reference tool and what the script actually delivers as reference material.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.