Back to skill

Security audit

金字塔写作法

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese writing workflow skill that helps structure documents using the Pyramid Principle, with no executable code, persistence, credential access, or hidden data handling found.

Install this if you want Chinese Pyramid Principle writing assistance. Expect it to favor Chinese headings, predefined templates, and structured outputs; for casual or non-Chinese writing, explicitly tell the agent your preferred language and format.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description and operational instructions prescribe a Chinese-language experience by default, but the file does not state that users may choose another language. This can violate language/locale policy where skills should not force a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad and includes common phrasing such as '帮我结构化' and '写一页纸', which can overlap with many ordinary writing requests and cause unintended skill activation. This is dangerous because an auto-invoked skill can steer user output into a rigid workflow, access referenced resources, and override user expectations even when the user did not explicitly request this writing mode.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The title '输出模板索引' indicates the skill content is presented in Chinese, and the file provides template-selection guidance entirely in Chinese without any opt-in or alternative language path. This can violate language/locale policy when a skill effectively forces a specific language for users regardless of preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file is entirely written in Chinese and frames the skill as a general-purpose writing coach, but it does not offer any language choice or state that the skill is intended only for Chinese-language users. Under the policy for natural-language constraints, forcing a specific language without user opt-in is a locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

At L140, the constraint includes "中文" as a required output language. Under the policy, forcing a specific language is a violation unless the skill offers a language choice or clearly justifies a locale-specific constraint, which is not present here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description says the preset applies when the user says “帮我用金字塔原理写”, but it does not define boundaries for when this shortcut should or should not activate. This phrase is broad enough to appear in ordinary writing-help requests, which could cause the preset to fill in missing context unexpectedly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file presents the skill purpose entirely in Chinese and does not indicate any user choice of language or locale. This can violate language/locale policy when a skill implicitly requires a specific language without documenting opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This markdown template contains substantial bilingual and English-only field labels such as 'Scenario', 'Audience', 'Goal', and 'Owner' while presenting itself as a general decision/review template. Because it does not state that the mixed-language format is optional or provide a user language preference, it may impose a language/locale convention without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The template content is written entirely in Chinese, with no indication that users may choose another language or locale. This can be a natural-language policy concern if the skill is expected to support users without mandating a specific language absent opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill guidance is entirely presented in Chinese and does not indicate that users may choose another language or locale. Per the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The constraint explicitly requires output in Chinese ("中文") for the external article scenario. Under the policy, forcing a specific language without offering the user a choice or documenting a justified locale restriction is a natural-language policy violation.

Content

No source excerpt is available for this finding.