ClawHub
Back to skill

Security audit

NLB

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple NLB helper whose login and account-data access are disclosed and aligned with checking library loans and recommendations.

Install only if you are comfortable using an agent-assisted browser flow with your NLB account. Enter credentials yourself when possible, do not let the agent store or repeat passwords or session tokens, and treat loan history and recommendations as private account information.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent/user to log into a third-party library account using myLibrary credentials, but provides no guardrails on handling authentication data, session state, or privacy-sensitive account information such as loan history and recommendations. In an agent setting, this can lead to credential exposure, improper collection of personal reading data, or unsafe automation of authenticated actions without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.