Back to skill

Security audit

电商印花裂变 | 印花多版本 | 图案裂变 | POD设计 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent image-design helper that uses the qhkit service, with ordinary dependency and account-token setup risks disclosed in the instructions.

Before installing, confirm you are comfortable letting the agent install or update qhkit/Node, store or use a qhkit token, upload the selected design image to the qhkit service, and spend account credits. Prefer a reviewed or pinned qhkit version if your environment has stricter supply-chain requirements.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description says the skill 'must trigger' for broad classes of common design requests, which can cause unintended invocation and expand the number of contexts where the skill gains influence over execution. In this skill, that matters because it also contains installation, configuration, and external service usage guidance, so overbroad triggering increases exposure to those risky behaviors.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill recommends executing npx @iqinghu/qhkit without pinning a specific version, which allows whatever package version is currently published to be fetched and executed at runtime. That creates a supply-chain risk: a compromised upstream package or malicious newly published version could run arbitrary code in the agent environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

This duplicate finding points to the same behavior: extracting Node into a user-controlled directory and prepending it to PATH. That is risky because it persists tooling in the user environment and can influence later commands, increasing the blast radius if the installed runtime or subsequent packages are compromised.

Content

Scanner excerpt · SKILL.md (reported line 52)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 duplicate finding points to the same behavior: extracting Node into a user-controlled directory and prepending it to PATH. That is risky because it persists tooling in the user environment and can influence later commands, increasing the blast radius if the installed runtime or subsequent packages are compromised.

Content

Scanner excerpt · SKILL.md (reported line 52)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
86% confidence
Finding

The instructions require use of the China-site iqinghu.com flow and explicitly direct the operator not to guide users to the international site unless the user clearly says they use it. This imposes a locale-specific workflow by default without offering a neutral language/locale choice or opt-in.

Content

No source excerpt is available for this finding.