ClawHub
Back to skill

Security audit

根据PRD或者你的测试用例来编写和修改测试用例

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent test-case writing guide with no executable payload, network behavior, persistence, or hidden data handling.

Install this if you want a Chinese-language assistant workflow for drafting and improving test cases. Be aware that its trigger terms are broad, so it may activate for general testing discussions, and users who need another output language may need to ask explicitly.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger instructions are broad enough to activate on many generic testing-related phrases, which can cause unintended routing of user requests into this skill. Misrouting can override more appropriate skills or workflows, increasing the chance of irrelevant file access, unnecessary tool use, or incorrect task handling in multi-skill environments.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
This JSON eval file contains all user prompts, expected outputs, and expectations in Chinese, which implicitly constrains the skill to a specific language. Under the policy, language-specific behavior should either be user-selectable or clearly documented as a justified locale-specific requirement, neither of which is present here.

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
The manifest description and invocation guidance are entirely in Chinese and do not state that language selection is optional or limited to a justified Chinese-only context. This can create a locale-policy issue if the skill effectively assumes a specific language without user opt-in.

Static analysis

No suspicious patterns detected.