Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
L03 写明“当用户要求视频画质提升、超分、超清修复、老视频变清晰、提升到 1080p/2K/4K 时必须触发”，其中“超分”“变清晰”等短语过于通用，容易和普通对话或泛化编辑需求重叠。该描述也没有提供排除条件或负例来界定何时不应触发此技能。
- Content
Security audit
AI视频超清修复 | 画质提升 | 超分辨率 | 视频增强 | 青虎AI
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed video-upscaling integration that installs and uses the qhkit CLI, uploads user-provided videos for processing, and does not show hidden or destructive behavior.
Install this only if you are comfortable using the qhkit npm CLI and sending selected videos to Qinghu AI for processing. Avoid using it for confidential, regulated, or third-party media unless you understand the provider's privacy and retention terms, and review any global npm or shell PATH changes before allowing them.
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
- 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 (7)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill notes that local file paths are accepted and that the CLI auto-uploads them, but it does not prominently warn users that local videos will be transmitted to a third-party service. In a skill handling potentially sensitive media, that omission can lead to unintentional disclosure of private or regulated content.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 94% confidence
- Finding
The skill instructs use of
npx @iqinghu/qhkitwithout pinning a specific version, which causes execution of whatever package version is current at invocation time. In a security-sensitive agent environment, that creates a supply-chain risk: a malicious or compromised upstream release could be fetched and executed automatically with the user's privileges.- Content
Session Persistence
Medium
- Category
- Rogue Agent
- Confidence
- 90% confidence
- Finding
This duplicate finding points to the same persistence behavior: installing executable tooling under the user's home directory and altering
PATHin a way that may survive normal use if copied into shell startup files. In an agent context, persistence-related instructions are riskier because they extend trust in third-party tooling beyond the immediate task.- Content
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:$PATH"
text
Session Persistence
Medium
- Category
- Rogue Agent
- Confidence
- 90% confidence
- Finding
This duplicate finding points to the same persistence behavior: installing executable tooling under the user's home directory and altering
PATHin a way that may survive normal use if copied into shell startup files. In an agent context, persistence-related instructions are riskier because they extend trust in third-party tooling beyond the immediate task.- Content
Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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
- 85% confidence
- Finding
L57 明确要求“本技能对接国内版 iqinghu.com”，并要求不要按国际站引导用户取密钥，整体流程默认单一地区站点和中文使用语境。该约束未向用户提供语言或区域选择，也未在文档中说明仅适用于特定地区用户的前提。
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
L15-L16 仅给出“帮我修一下/超分”“老素材变清晰”等正向示例，但未说明这些表达是否仅适用于视频、是否需要已有素材文件、以及与其他修复/编辑技能的区分边界。缺少限制条件会增加与常见用户表达的碰撞概率。
- Content