Back to skill

Security audit

皮亚杰建构写作法

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only teaching and writing workflow with no code execution, credential access, persistence, or hidden data movement.

Install this if you want a Chinese constructivist-writing workflow for lessons, explainers, and study notes. Users who want another output language should state that explicitly, because the bundled examples and templates are primarily in Chinese.

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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions are broad enough that ordinary user requests about writing, teaching, or beginner-friendly explanations could invoke this skill unintentionally. While the skill content itself is not harmful, over-broad activation can cause the agent to select an unintended workflow, leading to irrelevant behavior, missed user intent, or bypass of a more appropriate specialized skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file is a general-purpose writing template, but its user-facing title and most section labels are written in Chinese, which implicitly constrains use to a specific language/locale. There is no indication that this is optional, configurable, or justified as a region-specific template, so it conflicts with the policy against forcing a language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example input includes the explicit constraint "中文" as a required output language. This imposes a specific language preference in the skill's natural-language guidance without any indication that the user may choose another language or opt in to the locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Chinese, which can constitute a language/locale policy violation when no opt-in, alternative language option, or regional justification is provided. The policy specifically calls for flagging skills that force a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire preset document is written in Chinese and presents the skill guidance exclusively in that language. Under the policy rules, a skill that effectively enforces a specific language without offering an alternative or opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The sample request includes a hard constraint of “中文” for the output, which is a natural-language locale restriction. Under the policy criteria, forcing a specific language without user opt-in can be a language/locale policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.