ClawHub
Back to skill

Security audit

NEET

Security checks for vulnerabilities and agentic risk

Overview

This is a NEET study-planning skill with local progress tracking; its behavior is coherent with its stated purpose and no malicious execution or exfiltration behavior was found.

Install this if you want a NEET-focused study assistant that keeps local study records. Review or delete the ~/neet/ or ~/neet-tutor/ folders if you do not want exam profile details, performance history, category, domicile, or feedback retained locally.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
### Supporting Role
| If Child Says | Parent Should |
|---------------|---------------|
| "I'm stressed" | Listen, don't lecture |
| "I can't do this" | Reassure, offer help |
| "Leave me alone" | Give space, check later |
| "I need a break" | Grant reasonable breaks |
Confidence
85% confidence
Finding
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
5. **Section B strategy** — Identify easiest 10 quickly

### After Mock (same day)
1. **Score without checking answers** — Check marked questions
2. **Full analysis** — Which errors were silly vs concept
3. **Error log** — Record every mistake
4. **Revision list** — Topics to revisit
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill explicitly instructs the agent to persist user study data under ~/neet/, including profile details, performance history, exam category, domicile, and feedback, but provides no user-facing notice, consent step, or retention controls. While the data is educational rather than overtly dangerous, it still includes personal and potentially sensitive information that could be exposed to other local users, future sessions, or unintended tooling access.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
This markdown file is entirely framed around NEET-specific user types, assumptions, and category guidance, which reflects a specific regional/educational locale. Because the content does not explicitly state that it is intended only for NEET-context users or offer an opt-in/choice for other locales or exam systems, it can be read as forcing a locale-specific framework by default.

Static analysis

No suspicious patterns detected.