Back to skill

Security audit

Temu 商品图、主图套图、详情图、活动图生成 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Temu product-image helper, but users should notice that it installs and updates external CLI dependencies and stores an API token for a paid image service.

Before installing, confirm you are comfortable using qhkit from npm and sending product images plus an iqinghu API key to the service. Prefer a reviewed or pinned qhkit version when possible, avoid permanent PATH/profile edits unless you need them, and check the estimated credits before approving any generation task.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact version. That allows the fetched package to change over time, so a compromised upstream release or dependency could execute arbitrary code at runtime on the host.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
78% confidence
Finding

The same installation block recommends extracting binaries into a user-controlled directory and adjusting PATH, which creates session persistence and may influence later command resolution. In an agent setting, persistence is more dangerous because future unrelated tasks may inherit the modified toolchain and execute unexpected binaries.

Content

Scanner excerpt · SKILL.md (reported line 64)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

The same installation block recommends extracting binaries into a user-controlled directory and adjusting PATH, which creates session persistence and may influence later command resolution. In an agent setting, persistence is more dangerous because future unrelated tasks may inherit the modified toolchain and execute unexpected binaries.

Content

Scanner excerpt · SKILL.md (reported line 64)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
89% confidence
Finding

The prescribed user-facing onboarding text and instructions are entirely in Chinese and direct the agent to send that exact guidance to the user. There is no opt-in or alternative for users who may prefer another language, which creates a language-policy issue under the natural-language policy rules.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill falls back to npx --yes sharp-cli, which downloads and executes the latest package version on demand. Because this is an image-processing helper invoked automatically during remediation, it expands the attack surface to arbitrary upstream package changes and possible supply-chain compromise.

Content

No source excerpt is available for this finding.