ClawHub
Back to skill

Security audit

Writing Reboot Review

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese writing-coaching skill that asks reflective questions and produces writing-positioning advice, with no code execution, persistence, or hidden data access.

Install this if you want a Chinese-language guided writing retrospective. Expect it to ask about achievements, regrets, motivation, audience, and why writing stopped; avoid sharing private personal details you do not want used in the conversation.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
给出 3 个以内、可以立刻执行的动作。

## Output Rules

- 不要只做分析，必须落到动作
- 不要给超出当前阶段的复杂体系设计
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description includes broad trigger phrases such as general writing-direction and writing-help requests, which can cause the agent to invoke this deep-review workflow for ordinary tasks like ideation or light editing. Over-broad routing is risky because it can override user intent, collect unnecessary personal reflective information, and degrade safety by pushing a psychologically probing flow outside its intended scope.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The description, workflow, and example opening are entirely in Chinese and implicitly require Chinese-language interaction, but the file does not state that this is optional or limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.