ClawHub
Back to skill

Security audit

商品图消除 | 去水印 | 去除杂物 | 智能擦除 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed image-cleanup integration that installs and uses the qhkit CLI, with some supply-chain and environment-change cautions but no artifact-backed malicious behavior.

Install only if you are comfortable using the qhkit/iqinghu service for image editing, uploading the selected images to that service, and configuring a qhkit token. Prefer a reviewed or pinned qhkit version when possible, and avoid making permanent PATH or shell-startup changes unless you intentionally want this tooling available after the task.

A.I.G

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

SkillSpector

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
95% confidence
Finding

The trigger definition is very broad and says the skill must be invoked for common requests like removing text, watermarks, people, or clutter. In an agent setting, overly broad mandatory invocation can cause the system to route many unrelated or policy-sensitive requests to this external tool, increasing the chance of inappropriate data handling or policy bypass around watermark removal and image manipulation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which makes execution depend on the latest package state at runtime. That creates supply-chain risk: a compromised or breaking upstream release could be fetched and executed in the agent environment without review.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
86% confidence
Finding

This duplicated finding points to instructions for unpacking Node under the user's home directory and exporting a modified PATH. That creates session persistence and makes future commands rely on newly installed binaries, which is risky in agent environments because it extends the effect of the skill beyond the current operation.

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
86% confidence
Finding

This duplicated finding points to instructions for unpacking Node under the user's home directory and exporting a modified PATH. That creates session persistence and makes future commands rely on newly installed binaries, which is risky in agent environments because it extends the effect of the skill beyond the current operation.

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
86% confidence
Finding

The '何时触发' section gives examples like '清理一下这张图，只留商品', which could match multiple editing workflows such as background removal, cropping, or retouching. The document does not provide explicit non-matching examples in this section, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.