Back to skill

Security audit

Tutorial Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple tutorial-writing skill with no executable code, persistence, credential access, or hidden authority.

Installers should understand that this skill may activate for many tutorial or guide-writing requests, but its behavior is limited to formatting and structuring instructional content.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation guidance says to use the skill when the user asks to "create a tutorial, write a guide, explain how to use something, or document a process." Several of these phrases are broad, everyday requests that could match many unrelated conversations, and the file provides no exclusion conditions or narrower scope boundaries.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

md
- Use **bold** for key commands, file names, and important terms
- Use `code` for inline code, variables, and short commands
- Use blockquotes for warnings or notes:
  > **Note:** This step requires sudo privileges.
- Use numbered lists for sequential steps
- Use bullet points for non-sequential items

Static analysis

No suspicious patterns detected.