ClawHub
Back to skill

Security audit

Scroll

Security checks for vulnerabilities and agentic risk

Overview

This skill is low-privilege, but it is labeled as a Scroll blockchain reference while mostly providing generic finance and checklist boilerplate that could mislead users.

Install only if you understand this is a generic placeholder-style reference, not a reliable Scroll blockchain guide. Do not rely on it for smart contract, bridge, regulatory, compliance, or investment decisions without independent authoritative sources.

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 (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata and title present this as a Scroll blockchain reference tool, but the documented commands map to broad finance, regulation, and investment-style topics that do not clearly align with Scroll-specific blockchain operations. This mismatch can mislead users and downstream agents into trusting irrelevant or incorrect guidance in a blockchain context, increasing the risk of bad operational, compliance, or financial decisions.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest and file header claim this is a 'Scroll reference tool' for blockchain contexts, which implies content specifically about the Scroll blockchain ecosystem. Instead, the commands output broad placeholder material about regulations, risks, instruments, formulas, and checklists that are generic and not meaningfully tied to Scroll as a blockchain network or protocol.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The top-of-file comment explicitly states the skill should be used 'when working with scroll in blockchain contexts.' However, the implemented commands mostly emit vague, domain-agnostic boilerplate and even non-blockchain concepts, so the documentation materially misrepresents what the code actually provides.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.