Back to skill

Security audit

Claude Code Mastery

Security checks for vulnerabilities and agentic risk

Overview

This package is a low-risk Claude Code guide/template bundle, though it appears incomplete compared with its advertised contents.

Installers should treat this as a small prompt/template bundle, not the full advertised course: several promised deliverables are missing. From a security perspective, it does not execute code or request sensitive access; review any future added MCP setup scripts 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
  • 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)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The provided manifest context says the skill is 'Claude Code Mastery' and describes a guide to mastering the Claude Code CLI, but this file defines a skill named 'Security Audit' whose command performs vulnerability analysis on shared code. That is a direct semantic mismatch between the claimed skill purpose and the actual skill behavior defined here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This manifest describes the skill in very general terms ('Check code for security vulnerabilities' and 'Perform a security audit on the code I've shared') without any explicit trigger phrases, scope boundaries, or exclusion conditions. In a manifest file, this kind of broad invocation description can overlap with many ordinary requests about code review or analysis, increasing the chance of unintended activation.

Content

No source excerpt is available for this finding.