ClawHub
Back to skill

Security audit

Naming Forge

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only naming guidance skill with no code execution, installs, persistence, or hidden data handling.

Install this if you want naming and convention guidance. Be aware that useful results may require the agent to inspect relevant parts of your codebase for existing naming patterns, but the skill itself does not add executable code, persistence, network calls, or credential handling.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (2)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
├── POST   /users              → create user
├── PUT    /users/:id          → replace user
├── PATCH  /users/:id          → partial update
├── DELETE /users/:id          → delete user
├── POST   /users/:id/verify   → action on user (verb as sub-resource)

BAD:
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation section uses very broad, natural-language triggers such as naming something 'temp', reviewing misleading names, or starting a new module. In agent systems that auto-select skills from conversational intent, these generic triggers can cause the skill to activate unexpectedly, expanding its influence beyond tightly scoped user requests and potentially interfering with task routing or prompting behavior.

Static analysis

No suspicious patterns detected.