ClawHub
Back to skill

Security audit

电商图片翻译 | 图片文字翻译 | 多语言本地化 | 跨境翻译 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to perform disclosed e-commerce image translation through a third-party CLI, with installation and token-handling risks users should understand before use.

Install only if you are comfortable using qhkit and sending product images to the Qinghu service. Prefer a reviewed or pinned qhkit version when possible, avoid adding PATH changes to shell startup files unless needed, and treat the qhkit token like a credential. Review generated images manually for text, numbers, prices, logos, and product details before publishing.

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
93% confidence
Finding

The manifest description says the skill 'must trigger' whenever a user asks to translate image text or localize images into another language. While some examples are domain-specific, phrases like translating image text or changing an image to another language are broad enough to overlap with many ordinary requests, and the file does not provide negative examples or clear constraints on when not to invoke the skill.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact package version, which allows execution of whatever version is current at invocation time. That creates a supply-chain risk: behavior can change unexpectedly, or a compromised upstream release could execute unreviewed code in the agent environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This duplicate finding points to the same persistent user-local Node installation and PATH export workflow. Even with checksum verification, the skill is instructing durable environment changes that can affect later sessions and be leveraged by any later malicious package execution through the newly introduced runtime path.

Content

Scanner excerpt · SKILL.md (reported line 54)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
88% confidence
Finding

This duplicate finding points to the same persistent user-local Node installation and PATH export workflow. Even with checksum verification, the skill is instructing durable environment changes that can affect later sessions and be leveraged by any later malicious package execution through the newly introduced runtime path.

Content

Scanner excerpt · SKILL.md (reported line 54)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
88% confidence
Finding

The instructions require directing users to the domestic iqinghu.com site and state not to guide users using the international site unless they explicitly say they use it. This imposes a locale-specific workflow and Chinese-language/user-region assumption without presenting it as an opt-in choice or clearly limiting the skill to a documented region-specific audience.

Content

No source excerpt is available for this finding.