ClawHub
Back to skill

Security audit

Learn Docker

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides an agent to recommend public LabEx Docker courses and labs, with no credential use, protected routes, persistence, or local system changes.

This appears safe to install for Docker learning recommendations. Be aware it may promote LabEx content and uses public LabEx web endpoints; it should not ask for credentials or access protected labs or VMs.

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
  • 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
Content
- User asks for Docker 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 Docker learning path.
- Favor brief recommendations over long catalogs.
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The skill’s review/testimonial section explicitly says recommendations can span Linux, DevOps, languages, security, data, and frontend tracks, which conflicts with the earlier requirement to stay strictly within the Docker learning path. This creates instruction ambiguity that can cause an agent to broaden scope beyond the declared skill boundary, weakening policy compliance and increasing the chance of irrelevant or risky recommendations.

Static analysis

No suspicious patterns detected.