ClawHub
Back to skill

Security audit

yourtutor

Security checks for vulnerabilities and agentic risk

Overview

This is a simple exam-prep instruction skill that stays focused on user-provided study material and does not request risky access or run code.

Installers should expect this skill to keep answers tightly limited to the notes or PDF they provide. For best results, use it when you have both study material and a syllabus; for open-ended tutoring or general knowledge explanations, a normal tutoring skill may be less restrictive.

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
91% confidence
Finding

The trigger phrase "go through my syllabus" is broad enough to match many generic study-help interactions, which can cause the skill to activate when the user did not specifically request extraction strictly from provided materials. That can override normal assistant behavior and create confusing or policy-bypassing routing, especially because this skill insists on constrained behavior once activated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrase "quiz me on [topic]" is ambiguous because it applies to a very common class of tutoring requests and does not uniquely signal that this specialized skill should be used. An overly generic trigger increases unintended activation risk, potentially forcing the assistant into this skill's restrictive workflow even when the user wants general explanation, broader tutoring, or non-material-based quizzing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.