Back to skill

Security audit

Claude Code Mastery

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable Claude Code guide with command-template examples; its main issues are incomplete/missing advertised materials and light safety guidance, not malicious behavior.

Before installing, treat this as lightweight guidance and prompt templates, not a complete production package. Be especially careful with any MCP servers you add separately: use trusted sources, read-only or least-privilege credentials, and avoid connecting production databases or broad file-system access unless necessary.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The provided skill manifest context describes a skill named 'Claude Code Mastery' whose purpose is a guide to using the Claude Code CLI, but this file defines a different skill named 'Security Audit' that checks code for vulnerabilities. This is a direct semantic mismatch between the claimed purpose in the manifest context and the actual behavior described by the file.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill promotes MCP server setup and highlights database, GitHub/GitLab, API, and file system operations, but provides no safety framing about least-privilege configuration, secret handling, or the risk of broad local/system access. In an agent-skill context, this omission can lead users to connect powerful integrations that expose sensitive data or enable unintended destructive actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This manifest file describes activation in broad, generic terms like "Review changed files in current session" and "Review the changes I made in this session" without defining clearer trigger constraints or exclusion conditions. Those phrases overlap with common review requests and do not specify a narrow context, increasing the chance of unintended matching or invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The listed key commands include '/番茄', which imposes a specific locale/language example without clarifying whether alternatives exist or whether the user can choose their preferred language. SQP-3 applies to all file types and flags language or locale constraints that are not offered as an explicit choice.

Content

No source excerpt is available for this finding.