Back to skill

Security audit

Linux Edc9f0

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Linux learning guide with broad activation wording but no hidden execution, persistence, credential access, or destructive behavior.

Install only if you want a broad Linux video-note guide. Expect it may be invoked for general Linux questions, and independently verify any commands or installation advice from linked videos before running them.

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
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The top-level trigger includes very broad terms like "Linux" and generic course-title fragments, making accidental activation during ordinary conversation likely. This can cause the agent to invoke this skill in unrelated contexts, increasing the chance that unvetted, merged instructional content influences responses when the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation scenarios explicitly state that any user mention of "Linux" or need for "Linux-related help" can trigger the skill, which is far too broad for a common technical topic. Because the file aggregates content from multiple video-derived sources, unintended activation could inject irrelevant or low-trust guidance into many normal support interactions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

A nested embedded skill section repeats the same broad activation model, including generic "Linux-related help" language, which compounds collision risk across merged skills. Multiple overlapping broad triggers can make routing unpredictable and expand the blast radius of low-quality or unintended instructions across many Linux conversations.

Content

No source excerpt is available for this finding.