Back to skill

Security audit

电商商品替换 | 替换产品 | 保留场景换品 | 素材复用 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent LinkPix/qhkit image-editing helper with disclosed installation, token setup, and image-upload behavior, though users should understand the external CLI and API dependency before installing.

Install only if you are comfortable using the qhkit CLI and sending the selected product images, prompts, and API token configuration to iqinghu/LinkPix. For stricter environments, prefer a preinstalled or version-pinned qhkit package and avoid adding fallback Node paths to shell startup files unless needed.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Rogue AgentSelf-Modification, Session Persistence
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Rp1

Medium
Category
MCP Rug Pull
Confidence
83% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows execution of whatever package version is current at invocation time. That creates a supply-chain risk: a compromised or breaking upstream release could be fetched and run automatically in the agent environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
74% confidence
Finding

This duplicate finding points to the same behavior: extracting a runtime into the user's home directory and altering PATH, which can persist beyond the immediate task and influence subsequent executions. In an agent setting, persistence mechanisms are risky because they weaken reproducibility and can be leveraged by later malicious or compromised tooling.

Content

Scanner excerpt · SKILL.md (reported line 50)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
74% confidence
Finding

This duplicate finding points to the same behavior: extracting a runtime into the user's home directory and altering PATH, which can persist beyond the immediate task and influence subsequent executions. In an agent setting, persistence mechanisms are risky because they weaken reproducibility and can be leveraged by later malicious or compromised tooling.

Content

Scanner excerpt · SKILL.md (reported line 50)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
88% confidence
Finding

The instruction says the skill integrates with the domestic cn site and explicitly tells the agent not to guide users to the international site unless the user clearly states they use it, while the surrounding operational text and user-facing messages are all prescribed in Chinese. This creates a locale/language constraint without presenting a user option to choose another language or locale.

Content

No source excerpt is available for this finding.