ClawHub
Back to skill

Security audit

AI生成电商pod素材 | 印花提取 | 印花贴合 | 印花裂变 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed POD image-generation helper that uses the qhkit CLI and external image service, with install and token setup risks users should approve explicitly.

Install only if you intend to use LinkPix/qhkit for POD image generation. Approve any npm, Node, PATH, or token configuration changes deliberately, prefer a pinned qhkit version where possible, and remember that local images sent to qhkit are uploaded to the provider and may consume account credits.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (5)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill 'must trigger' on broad POD/design keywords, which can cause the agent to activate this skill in many ordinary conversations. Over-broad auto-triggering is dangerous because it can steer users into running installation, configuration, and external-tool workflows that were not explicitly requested, expanding the attack surface and creating opportunities for unintended command execution guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill contains detailed installation and network download steps that modify the local environment, including global npm installs, manual Node installation, PATH changes, and persistent shell profile suggestions, but it does not clearly require user consent before making those changes. This is risky because a broadly triggered skill may lead an agent to alter the system, fetch software from the network, and configure credentials without an explicit warning or approval checkpoint.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The skill recommends running npx @iqinghu/qhkit <命令> ... without pinning a specific version. That allows execution of whatever package version is current at invocation time, increasing supply-chain risk if a bad release or account compromise occurs. In a skill that instructs users to install and execute CLI tooling, this is more dangerous because it directly drives code execution on the host.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
82% confidence
Finding

This duplicate finding points to the same user-directory install and PATH modification sequence. Persistent user-level runtime installation is not inherently malicious, but in a skill that can auto-trigger and instruct shell actions, it increases risk by making environment changes that may affect subsequent sessions and tooling resolution.

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
82% confidence
Finding

This duplicate finding points to the same user-directory install and PATH modification sequence. Persistent user-level runtime installation is not inherently malicious, but in a skill that can auto-trigger and instruct shell actions, it increases risk by making environment changes that may affect subsequent sessions and tooling resolution.

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