ClawHub
Back to skill

Security audit

电商服装多姿势套图 | 模特姿势生成 | 多角度展示 | 服装套图 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent image-generation helper, but users should be aware it may install or update a CLI package and upload model photos to Qinghu AI.

Before installing, confirm you are comfortable installing or updating the qhkit npm package and providing a Qinghu AI token. Generated image requests may upload the referenced model photo to the service, so avoid using private or sensitive images unless that is intended.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

L03 使用了“当用户要求模特多姿势、多角度展示图、服装套图、一张模特图出一组时必须触发”这类宽泛表述，并混合大量关键词，没有明确排除条件或负例。像“多角度”“出一组”这类短语可出现在一般图片编辑请求中，容易与相邻技能能力重叠，造成非预期调用。

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill explicitly recommends falling back to npx @iqinghu/qhkit <命令> without pinning a version. Unpinned npx execution fetches and runs the latest package at invocation time, which creates a supply-chain risk and undermines reproducibility if the upstream package is compromised or changed unexpectedly.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
78% confidence
Finding

This duplicated finding points to the same behavior: unpacking software into a persistent user directory and exporting a modified PATH. In an agent context, self-installation and environment mutation are risky because they normalize making lasting system changes in order to complete a task, which can be abused or have unintended downstream effects.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

Linux 二进制安装（装到用户目录，无需 root；先校验官方 SHA256 再解包）：

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Session Persistence

Medium
Category
Rogue Agent
Confidence
78% confidence
Finding

This duplicated finding points to the same behavior: unpacking software into a persistent user directory and exporting a modified PATH. In an agent context, self-installation and environment mutation are risky because they normalize making lasting system changes in order to complete a task, which can be abused or have unintended downstream effects.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

L60 明确要求“不要按国际站引导用户取密钥，也不要拿国际站的模型清单答复”，并指定返回内容采用国内版对应文案体系，但未体现用户可选择语言/站点或基于用户偏好切换。这会在自然语言交互中强制施加特定语言/区域方案，存在语言/locale 政策风险。

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

L13-L16 仅给出两个正向示例，其中“服装详情页需要正面/侧面/背面/细节多机位素材时”描述的是业务场景而非清晰的触发短语，也未说明哪些近邻需求不应触发。缺少边界说明会让代理难以区分本技能与一般商品图生成、换装或修图请求。

Content

No source excerpt is available for this finding.