ClawHub
Back to skill

Security audit

AI人味写作技

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese writing-revision skill with broad style guidance, but no evidence of hidden execution, data theft, persistence, or unsafe system changes.

Install this if you want a prescriptive Chinese creative-writing and anti-AI-style revision workflow. Be explicit about language and editing boundaries when invoking it, especially for non-Chinese text or files you do not want modified.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill metadata and content strongly frame the tool as Chinese-only and target Chinese writing scenarios, without indicating that language choice should follow user preference. If auto-invoked, this can override the user’s requested language or transform non-Chinese writing tasks into Chinese-oriented behavior, causing unwanted prompt steering and loss of user control.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list is broad and includes very common writing requests such as 润色, 改写, humanize, and 中文写作, which can cause the skill to activate for many unrelated user prompts. Over-broad activation increases the chance that this skill will intercept general writing tasks and steer outputs toward its prescriptive style and language constraints without explicit user intent.

Static analysis

No suspicious patterns detected.