Back to skill

Security audit

avoid-ai-writting-flavor

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown writing-guidance skill for academic manuscripts, with no code, persistence, credential access, or hidden execution behavior.

Install this if you want strong, prescriptive academic-writing cleanup guidance. Be aware it may activate on broad academic writing tasks and its guidance is written in Chinese, so users should ensure it matches their language and editing expectations.

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
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation condition is broad enough to trigger on general writing, editing, or reviewing of academic papers, not just narrowly scoped AI-style mitigation tasks. This can cause the agent to inappropriately apply prescriptive transformations or workflow requirements in unrelated contexts, reducing reliability and potentially overriding user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill content is entirely in Chinese and provides no user-choice or locale justification, which can force a language switch unrelated to the user's request. In an agent setting, this can degrade usability, cause misunderstandings, and lead to incorrect edits or reviews if the user expects another language.

Content

No source excerpt is available for this finding.