ClawHub
Back to skill

Security audit

Linea

Security checks for vulnerabilities and agentic risk

Overview

This skill is low-permission and does not show malware-like behavior, but it claims to be a Linea blockchain reference while providing generic placeholder finance and compliance text.

Install only if you understand this appears to be a static, generic reference script rather than a reliable Linea blockchain guide. It does not appear to access sensitive data or persist on the system, but its content should not be relied on for blockchain, compliance, or financial decisions without independent verification.

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 (2)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The inline description explicitly claims blockchain-specific Linea support, while the embedded text treats 'Linea' as a vague placeholder concept. In an agent skill ecosystem, this increases the risk of deceptive capability signaling, where users or agents invoke the tool expecting authoritative blockchain guidance and instead receive irrelevant or fabricated reference material.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is presented as a Linea blockchain reference tool, but the command content is generic finance/compliance material and does not actually provide Linea-specific blockchain guidance. This mismatch can mislead users and downstream agents into trusting inaccurate domain content, causing incorrect decisions in blockchain-related workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.