Back to skill

Security audit

zh-de-ai-if

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown Chinese writing-style skill with no executable code, hidden persistence, or credential access.

Install this if you want Chinese text rewritten to sound more natural and less templated. For sensitive legal, academic, medical, financial, or compliance writing, use only light edits and review any source-checking or factual-change suggestions yourself.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 77)May include surrounding context.

其中主技能文件必须是:

text
skills/zh_de_ai_ify/SKILL.md

改写强度

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The title and core instruction define the skill around rewriting Chinese text, and the document does not indicate that language selection is optional or user-controlled. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy concern unless the restriction is explicitly justified and documented.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger phrases are very broad and colloquial, so this skill may activate for generic writing-assistance requests where the user did not specifically ask for 'de-AI-ification'. That can cause scope confusion and unintended rewriting behavior, but it does not create a direct security exploit path or privilege escalation by itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file title and description state that this is a Chinese-only rule glossary for the zh_de_ai_ify skill, but there is no user opt-in, alternative locale support, or explicit justification for enforcing Chinese. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

技能清单前半部分都围绕中文措辞、结构和风格润色,但这里新增了“链接是否能打开”“论文/报告是否真实存在”“DOI / ISBN 是否有效”等事实核验任务。这类工作属于外部来源验证与内容真实性审查,不是该 manifest 所声明的文本去模板味、去官话味所必需或显然内含的实现细节。

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

“链接是否能打开”“来源是否支持原文说法”“DOI / ISBN 是否有效”代表一种验证外部信息真伪与可访问性的能力。对于一个宣称用途是让中文文本更自然、更像真人表达的润色技能,这种能力并非直接且明显的必要条件。

Content

No source excerpt is available for this finding.