ClawHub
Back to skill

Security audit

Ai Agent Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language agent-builder skill whose deployment and tool-use examples are disclosed and purpose-aligned, though users should scope permissions carefully.

Before using deployment or agent-run commands, review which tools the agent will receive, especially email and database access. Start in a test environment, grant least-privilege permissions, and monitor deployed agents for unintended actions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises deployment and execution capabilities for custom agents, including a deploy command, but does not clearly warn that these actions can create or run system-affecting automations. In a builder-style skill, users may deploy agents with integrated tools like email, search, or databases without understanding the operational or security consequences, increasing the risk of unintended actions or over-privileged deployments.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The file presents the skill description, examples, and cautions entirely in Chinese, which effectively forces a specific language for users without indicating opt-in or a justified regional limitation. The policy requires avoiding language or locale constraints unless the user is given a choice or the restriction is clearly documented.

Static analysis

No suspicious patterns detected.