Back to skill

Security audit

ARG Action Chain Designer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language skill for designing structured agent workflows, with file generation only tied to user-requested deliverables.

Install this if you want a Chinese-language assistant for designing ARG-style agent workflows. Expect it to propose or create SKILL.md, plans, output directories, and validation script drafts when you ask for file-level deliverables, and review any generated scripts or Bash-enabled runtime chains before executing them.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (10)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
这个 skill 不应该只给一段建议就结束。默认先产出可落地的设计;当用户需要文件级交付物时,继续生成薄 `SKILL.md` 引擎、`plans/step-*.md`、必要的 `scripts/` 草案。若用户已经明确说“创建、生成、写入、落地、打包”,且当前工作区可写,就直接生成文件。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 158)May include surrounding context.

md
这个 skill 不应该只给一段建议就结束。默认先产出可落地的设计;当用户需要文件级交付物时,继续生成薄 `SKILL.md` 引擎、`plans/step-*.md`、必要的 `scripts/` 草案。若用户已经明确说“创建、生成、写入、落地、打包”,且当前工作区可写,就直接生成文件。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 183)May include surrounding context.

md
这个 skill 不应该只给一段建议就结束。默认先产出可落地的设计;当用户需要文件级交付物时,继续生成薄 `SKILL.md` 引擎、`plans/step-*.md`、必要的 `scripts/` 草案。若用户已经明确说“创建、生成、写入、落地、打包”,且当前工作区可写,就直接生成文件。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 184)May include surrounding context.

md
这个 skill 不应该只给一段建议就结束。默认先产出可落地的设计;当用户需要文件级交付物时,继续生成薄 `SKILL.md` 引擎、`plans/step-*.md`、必要的 `scripts/` 草案。若用户已经明确说“创建、生成、写入、落地、打包”,且当前工作区可写,就直接生成文件。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description and all invocation examples are written entirely in Chinese, and there is no indication that users may interact in other languages or choose their preferred locale. Under the policy, a skill that implicitly requires a specific language without opt-in is 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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document title and core instruction require responses in Chinese ('输出模式', '按用户请求选择一个模式'), and the entire skill guidance is written as a fixed Chinese-output template without offering any language choice. This creates a natural-language locale policy issue because it effectively forces a specific language absent user opt-in or a documented region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file presents the skill template entirely in Chinese, beginning with a Chinese title, and does not offer any language choice or note that the template is intended only for a Chinese-speaking context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example output explicitly requires a Chinese summary ("中文概括") and uses a Chinese sentiment label ("正向") without indicating that language is configurable or user-selected. This creates a natural-language policy concern because it forces a specific language/locale by default rather than offering opt-in or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description says that if the user confirms and the workspace is writable, it should directly create or modify files. While this is part of the skill's purpose, the markdown does not include an explicit warning that running the skill may alter workspace files, which is the kind of user-impacting behavior SQP-2 asks markdown files to disclose.

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 markdown file is written in Chinese and provides no indication that users may choose another language or that the locale restriction is required for a region-specific purpose. Under the policy rule for language or locale constraints, this is a natural-language policy issue because it implicitly enforces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.