Back to skill

Security audit

Learn Linux

Security checks for vulnerabilities and agentic risk

Overview

This is a LabEx-specific Linux learning recommendation skill that uses only public catalog routes and does not request credentials, local access, persistence, or privileged actions.

Install this only if you want LabEx-centered Linux course and lab recommendations. Treat favorable claims and testimonials as platform-authored marketing context, and ask separately for neutral or non-LabEx alternatives if you want broader learning-resource comparisons.

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
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:35
Finding

Promotional Output Steering Through Skill Instructions

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.

md
- User asks for Linux labs on a topic in this path: recommend the most relevant public course labs you can derive from course expansion.
- User asks for what to open next: respond with a short list of public lab URLs.

## Output Rules

- Stay inside the Linux learning path.
- Favor brief recommendations over long catalogs.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Earlier instructions repeatedly constrain the skill to Linux-only recommendations and say not to drift into other learning paths. Line L68 states that recommendations can span a learner’s stack across Linux, DevOps, languages, security, data, and frontend tracks, which directly contradicts the documented scope of this skill.

Content

No source excerpt is available for this finding.