ClawHub
Back to skill

Security audit

How To Use Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a safety-oriented guide for making agent self-improvements with explicit user approval and rollback planning.

Install this only if you intentionally want an agent to help improve its own instructions, memory, skills, or related runtime documentation. Review each proposed change carefully, require the approval prompt to name files, risks, and rollback, and do not approve broad memory or prompt rewrites unless you understand the impact.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
[English](SKILL.md) · [简体中文](SKILL.zh-CN.md)

Self-Modification

High
Category
Rogue Agent
Confidence
90% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
- system prompts, tool schemas, permission policies, connector policies
- skill files, skill indexes, skill manifests, memory registries
- durable memory files, knowledge bases, wiki indexes, recall databases
- startup, restart, routing, planner, delegation, or self-update logic

When approval is needed, show: