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 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkPix/qhkit workflow for product-image enhancement, with expected but noteworthy external uploads, token use, and local package installation.

Install only if you are comfortable using the qhkit/LinkPix service, providing its API token, and uploading the selected product images to that service. Confirm before installing or upgrading npm packages, adding Node under your home directory, or spending credits on generation.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (6)

Vague Triggers

High
Category
Not specified by scanner
Confidence
94% confidence
Finding

The metadata says the skill 'must trigger' for broad, common requests like image optimization and quality improvement. This overbroad routing can cause the agent to invoke an external tool unnecessarily, increasing the chance of unintended file handling, network access, or user redirection to third-party services.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The example trigger phrases are vague and overlap with ordinary image-editing requests, without boundaries that distinguish this skill from more general capabilities. In practice this can misroute unrelated user tasks into a tool-driven workflow that may upload local images or initiate external processing unnecessarily.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which permits execution of whatever package version is current at runtime. In a security-sensitive agent context, this creates a supply-chain risk: a compromised latest release or dependency could be fetched and executed automatically.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking software into a user-controlled directory and prepending it to PATH. Even though the instructions include checksum verification, the resulting environment mutation persists beyond the immediate action and can influence subsequent sessions or tool resolution.

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
88% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking software into a user-controlled directory and prepending it to PATH. Even though the instructions include checksum verification, the resulting environment mutation persists beyond the immediate action and can influence subsequent sessions or tool resolution.

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
84% confidence
Finding

The file instructs the agent to send domestic-site key retrieval wording and states that CLI messages are already user-facing Chinese to be relayed as-is. This imposes a specific language/locale behavior without offering the user a language choice or making the locale restriction explicit as a user opt-in requirement.

Content

No source excerpt is available for this finding.