Back to skill

Security audit

电商白底图生成 | 批量抠图 | 去背景 | 透明底图 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ecommerce image workflow that installs and uses qhkit to generate white-background product images, with some normal dependency and setup risks.

Install only if you are comfortable sending product images to the qhkit/iqinghu service and installing its npm CLI. Prefer a reviewed or pinned qhkit version for reproducibility, avoid adding PATH changes to shell startup files unless you want a permanent setup, and verify generated product details because the workflow is generative rather than pixel-preserving.

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 manifest says the skill "must trigger" whenever a user asks to cut out an image, remove a background, or make a pure-color background, and then lists many broad keywords. Several of these phrases are common image-editing requests that can overlap with other tools or contexts, and the file does not provide exclusion conditions or negative examples to narrow invocation scope.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The skill recommends invoking npx @iqinghu/qhkit without a pinned version, which can pull whatever package version is current at execution time. That creates a supply-chain risk: behavior can change unexpectedly, and a compromised or malicious upstream release could be executed immediately in the user's environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
78% confidence
Finding

The same installation block creates durable local state by unpacking binaries into a user-owned directory and exporting a new PATH, potentially persisting across sessions if added to shell startup files. While not inherently malicious, this changes the execution environment in a way that can be abused or can mask system binaries later.

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
78% confidence
Finding

The same installation block creates durable local state by unpacking binaries into a user-owned directory and exporting a new PATH, potentially persisting across sessions if added to shell startup files. While not inherently malicious, this changes the execution environment in a way that can be abused or can mask system binaries later.

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

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The markdown gives a couple of example requests and a general condition about marketplace white-background requirements, but it does not clearly state when the skill should not activate. Without explicit exclusions, requests like generic background removal or non-ecommerce edits could unintentionally route here.

Content

No source excerpt is available for this finding.