ClawHub
Back to skill

Security audit

Sui Move

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Sui Move development reference skill with expected documentation setup and CLI examples, but users should treat publish/call examples as real blockchain operations when run.

Install this only if you want Sui/Move development assistance and are comfortable with it installing or using the Sui CLI and downloading official Sui/Move documentation. Before running any `sui client publish` or `sui client call` command, check the active network, wallet address, gas budget, and package contents, and prefer devnet or testnet until you intentionally deploy.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description activates on broad terms like 'blockchain development on Sui' and related smart-contract topics without tighter scoping, which can cause the skill to trigger for general blockchain discussions rather than clearly bounded Sui/Move tasks. Over-broad activation increases the chance that operational guidance, commands, or code patterns are surfaced in contexts where the user did not explicitly request them, leading to unintended tool use or risky blockchain advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill provides sui client publish guidance but does not warn that publishing submits an on-chain transaction, consumes SUI gas, and may have irreversible effects once executed. In a blockchain-development skill, omission of this warning is more dangerous because users may copy commands directly and unintentionally spend funds or deploy code to a live network.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.