ClawHub
Back to skill

Security audit

AI视频超清修复 | 画质提升 | 超分辨率 | 视频增强 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent video upscaling integration, but users should understand that it may install command-line dependencies and upload local videos to the qhkit/iqinghu service for processing.

Before installing, confirm you are comfortable using the iqinghu/qhkit service, installing or updating its npm CLI, and uploading any local videos you ask it to enhance. Avoid sending sensitive or private media unless you trust that service and account configuration.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

L15-L16 将“帮我修一下/超分”“老素材变清晰”等自然表达列为触发示例，且 L03 还写明“当用户要求…时必须触发”，但没有排除场景或负例。这些表述在一般视频编辑对话中也很常见，容易与其他修复、剪辑或增强类技能重叠。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill states that local file paths are accepted and that the CLI will automatically upload them, but it does not require an explicit user-facing consent step before transmission to a third-party service. In a file-processing skill handling local videos, this is security-relevant because sensitive local media may be exfiltrated off-host without sufficiently prominent disclosure or confirmation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill recommends executing npx @iqinghu/qhkit without pinning an exact version, which allows whatever package version is current at execution time to run code in the user's environment. In a supply-chain compromise or malicious update scenario, this creates a real remote code execution risk because npx downloads and executes package code on demand.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
71% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking Node into $HOME/.local/lib and exporting a modified PATH for subsequent command execution. In the context of an agent skill, bootstrapping and persisting executables locally is risky because it shifts the skill from simple task orchestration into environment modification with long-lived effects.

Content

Scanner excerpt · SKILL.md (reported line 50)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
71% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking Node into $HOME/.local/lib and exporting a modified PATH for subsequent command execution. In the context of an agent skill, bootstrapping and persisting executables locally is risky because it shifts the skill from simple task orchestration into environment modification with long-lived effects.

Content

Scanner excerpt · SKILL.md (reported line 50)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
81% confidence
Finding

L57 明确要求对接“国内版 iqinghu.com”，并强调“不要按国际站引导用户取密钥，也不要拿国际站的模型清单答复”，同时 L82 规定转述“面向用户的中文”。这会将用户限制在特定站点/语言流程下，未提供语言或区域偏好选择。

Content

No source excerpt is available for this finding.