ClawHub
Back to skill

Security audit

Building Study Guides

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only uNotes study-helper workflow with clear limits and no evidence of hidden execution, persistence, or data exfiltration.

Before installing, users should understand that the skill can read selected uNotes document text through the uNotes connector to generate study content in chat. It appears read-only and purpose-aligned, but users should only invoke it for notes they are comfortable sharing with the chat session.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description says to use the skill when the user asks to 'summarize these notes' or 'help me study for my exam', which are broad, natural phrases that could match many ordinary conversations. Although the sentence later narrows this to uNotes material, it does not provide explicit exclusion examples or a clearly bounded trigger list, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.