Back to skill

Security audit

商品详情页文案

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly scoped Chinese product-copywriting guidance, with a routine installation caveat and no hidden access or automation found.

Use this skill for Chinese product-copy drafts and check factual claims before publishing. If using the README installer, prefer a reviewed installer version and a fixed skill revision because the documented command can fetch changing versions.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (12)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The only supplied command performs skill installation, which is not disclosed in the declared purpose. No supplied code processes merchant information, produces copy, attaches supporting evidence, or requests missing materials. This assessment is limited to the installation command; the installed skill's behavior is not shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

所给代码的直接用途是安装或添加外部技能,与声明的商品详情页文案撰写用途不同。外部技能名称虽然与声明主题相关,但不能据此确认其实现了所述功能;该外部技能的实际行为未包含在本次提供的代码中。

Content

No source excerpt is available for this finding.

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.en.md (reported line 29)May include surrounding context.

md
## Attribution and license

The use case was informed by [marketingskills](https://github.com/coreyhaines31/marketingskills) and its [copywriting Skill](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md). This repository's Chinese instructions, workflow, and examples are original and do not copy their source or copy. Licensed under [MIT-0](LICENSE).

## Install

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 49)May include surrounding context.

md
## 来源与许可

本 Skill 的用途参考了 [coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills) 及其 [copywriting Skill](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md)。本仓库的中文说明、工作流与样例均为原创,未复制其源码或文案。许可证为 [MIT-0](LICENSE)。

## 安装

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 · manifest.yaml (reported line 40)May include surrounding context.

yaml
promo: assets/promo-1600x900.png
sources:
  - https://github.com/coreyhaines31/marketingskills
  - https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The installation command invokes the npm package skills through npx without pinning a version, potentially downloading and executing a changing package release with the installing user's privileges. This is an installation-time supply-chain risk, not an MCP server reference; the README provides no evidence of malicious behavior, and its Markdown-only runtime scope limits ongoing exposure but does not remove installation risk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The installation command invokes an unpinned npm CLI through npx, which can download and execute a changing package version with the installing user's permissions. This creates a supply-chain exposure if a future release is compromised; however, this is a conventional installation instruction, not an MCP server reference or evidence of malicious behavior, and it does not execute automatically from the Markdown.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The default prompt explicitly requires Chinese output without offering a language choice.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The default prompt instructs the agent to write Chinese product-detail pages (“撰写中文商品详情页”), rather than simply using Chinese to describe the skill. The manifest provides no language-selection mechanism or justification for enforcing this output language.

Content

No source excerpt is available for this finding.

The skill requires Chinese-language output without offering a language choice or opt-in.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The descriptions explicitly specify generating Chinese product-detail copy, rather than choosing the output language based on user preference. Although Chinese copywriting is advertised as the skill's purpose, the manifest provides neither a language-selection mechanism nor a regional requirement justifying the restriction.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

The skill requires Chinese-language output without offering a language choice or documenting a locale-specific justification.

Low
Category
Output Handling
Confidence
91% confidence
Finding

The instruction explicitly requires Chinese product-detail copy, and the description at L03 reinforces that requirement. Although the skill name includes “cn,” the file does not offer language opt-in or explain a regional requirement that justifies restricting the output language.

Content

No source excerpt is available for this finding.