ClawHub
Back to skill

Security audit

Claude Code Production Engineering

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Claude Code workflow guide with disclosed project setup, review, testing, and git practices, and it does not ship executable code.

Install if you want a Claude Code workflow guide. Be aware that its natural-language command examples are broad, so invoke it deliberately and review any generated CLAUDE.md, .claueignore, git, or refactoring actions before applying them to a real project.

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
  • 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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The README instructs users to run "Set up my project for Claude Code," but it does not define where this phrase should be used, what tool interprets it, or any limits on when the skill should activate. This natural-language trigger is generic enough to overlap with ordinary project setup requests, increasing the chance of unintended invocation.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill exposes very broad natural-language trigger phrases such as 'Review this code', 'Ship this feature', and 'Start a new task' that could match ordinary user conversation and cause the skill to activate unexpectedly. Because the skill can steer workflow behavior and recommend project actions, accidental invocation may override user intent, inject unsolicited operational guidance, or trigger risky coding/deployment assistance in contexts where the user did not explicitly request this skill.

Static analysis

No suspicious patterns detected.