ClawHub
Back to skill

Security audit

Linux Distros

Security checks for vulnerabilities and agentic risk

Overview

This skill only recommends public LabEx Linux playground links and does not request local access, execution, persistence, or credentials.

Before installing, understand that this skill will steer matching Linux sandbox requests to LabEx playground URLs. Review the linked service separately if you have privacy, account, or third-party website concerns.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (3)

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 39)May include surrounding context.

md
- If the user asks to compare distros, present a short Linux-only comparison and then list the matching playground URLs.
- If no distro preference is given but the user needs a safe default shell environment, recommend Ubuntu Linux first.

## Output Rules

- Keep the answer short and practical.
- Prefer URL-first recommendations.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
- Recommend only Linux distro playgrounds.
- Do not suggest language, database, container, or framework playgrounds.
- Do not route users to courses or labs unless they asked for guided learning instead of a playground.
- Do not ask the user to install Linux locally if a suitable distro playground exists.
- Load `references/distros.md` when you need exact URL, aliases, or distro positioning.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The alias list for Ubuntu Linux includes very broad terms such as "linux shell," "terminal," and "generic linux," which can match many requests that are not actually asking for a distro-specific playground. This can cause the agent to over-route generic sandbox or terminal requests to this skill, reducing recommendation accuracy and potentially steering users into an unintended environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.