ClawHub
Back to skill

Security audit

Writing Polish

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese writing-polish instruction file with no code, persistence, credentials, or system access, though its trigger language is somewhat broad.

Install this if you want Codex to polish or rewrite Chinese prose in a concrete, plainspoken style. Be explicit when you do not want Chinese output, translation, or stylistic rewriting.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation description is very broad and can match many ordinary requests involving writing, rewriting, polishing, or even implied dissatisfaction with text quality. In a skill-routing system, this can cause the skill to trigger when the user did not explicitly want this behavior, creating prompt-scope confusion, unwanted transformation of user content, and increased chances of instruction precedence conflicts with other skills or the base assistant.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill hard-codes a Chinese-writing assistant role and strongly implies Chinese output without checking the user's current language or preference. This can override user intent, degrade reliability in multilingual contexts, and create prompt-instruction conflicts where the skill's role framing takes precedence over what the user actually asked for.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.