Back to skill

Security audit

AI电商主图优化 | 主图美化 | 点击率提升 | 图片增强 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-built for Qinghu product-image generation, but it asks agents to install and update tools, use persistent configuration, upload images, and spend credits under trigger rules that are too broad.

Install only if you intend to use the China-region Qinghu qhkit service for e-commerce product images. Confirm before uploading local images or spending credits, prefer a pinned and reviewed qhkit version, avoid adding PATH changes to shell startup files unless you want them to persist, and keep API tokens scoped and removable.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The metadata says the skill 'must trigger' for broad, common requests like image optimization or improving quality. In an agent environment, overly broad mandatory triggers can cause unintended invocation, leading to unexpected external tool use, uploads, installation attempts, or paid API consumption without sufficiently specific user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example trigger phrases are generic and can match many benign photo-editing requests outside the intended e-commerce main-image use case. Because this skill performs generation, installation, and remote-service interaction, ambiguous activation increases the chance of unintended execution and user data transfer.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows whatever package version is current at execution time to be fetched and run. That creates a supply-chain risk: a compromised or breaking upstream release could execute unexpected code or change behavior in a privileged automation context.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
86% confidence
Finding

The skill directs installation of Node into $HOME/.local/lib and suggests adding it to PATH, including guidance to append PATH changes to ~/.bashrc. This creates persistence beyond the immediate task and modifies the user environment, which is risky in agent contexts because it changes future command resolution and can outlive the current session.

Content

Scanner excerpt · SKILL.md (reported line 54)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
86% confidence
Finding

The skill directs installation of Node into $HOME/.local/lib and suggests adding it to PATH, including guidance to append PATH changes to ~/.bashrc. This creates persistence beyond the immediate task and modifies the user environment, which is risky in agent contexts because it changes future command resolution and can outlive the current session.

Content

Scanner excerpt · SKILL.md (reported line 54)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
90% confidence
Finding

The instructions require directing users to China-specific iqinghu.com flows and state that CLI messages are already user-facing Chinese to be relayed as-is. This imposes a locale/language expectation without opt-in or an alternative path for users who may need another language or region.

Content

No source excerpt is available for this finding.