Back to skill

Security audit

电商场景图生成 | 场景合成 | 商品场景 | 营销场景图 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkPix/qhkit workflow for generating product scene images, with some install and account-configuration risks users should understand before use.

Install only if you are comfortable using the qhkit npm package and sending product images/prompts to the LinkPix/iqinghu service. Check whether you use the domestic iqinghu.com account or an international AutoAGC account before setting tokens, and prefer reviewed or pinned dependency versions in controlled environments.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says scene-image requests '必须触发', with many broad keywords spanning multiple ecommerce and lifestyle contexts. This can cause the skill to activate in unintended situations, sending user inputs or local files into image-generation workflows without sufficiently precise user intent confirmation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The '何时触发' section provides only positive examples and lacks negative boundaries, disambiguation rules, or cases where similar phrases should not invoke the skill. In an agent setting, vague activation criteria increase accidental tool use and unintended disclosure of prompts, files, or tokens to the external CLI/service.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The skill explicitly recommends falling back to npx @iqinghu/qhkit <命令> without pinning a version. That allows execution of whatever package version is current at invocation time, creating a supply-chain risk if a malicious or broken release is published or if dependency resolution changes unexpectedly.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

This finding duplicates the same persistent install-and-PATH modification behavior at the same location. The guidance normalizes writing binaries into the user's home directory for reuse, which creates session persistence and makes later executions depend on artifacts fetched during a prior run.

Content

Scanner excerpt · SKILL.md (reported line 56)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
84% confidence
Finding

This finding duplicates the same persistent install-and-PATH modification behavior at the same location. The guidance normalizes writing binaries into the user's home directory for reuse, which creates session persistence and makes later executions depend on artifacts fetched during a prior run.

Content

Scanner excerpt · SKILL.md (reported line 56)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
93% confidence
Finding

The skill instructs the agent to force the domestic cn site configuration and override existing intl settings unless the user explicitly says otherwise. That can reroute authentication and API usage to a different service region without clear user consent, risking account misuse, privacy issues, and misdelivery of user data or credentials.

Content

No source excerpt is available for this finding.