Back to skill

Security audit

AI视频翻译 | 视频字幕翻译 | 视频语音翻译 | 视频本地化 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed video-translation CLI skill, with the main caveat that it may install qhkit or Node and use a user-provided API token.

Install only if you are comfortable running the @iqinghu/qhkit npm package and giving it an API token. Confirm before global installs, Node bootstrap, PATH or bashrc changes, and remember that video files you provide may be uploaded to the qhkit service for processing.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

L03 将多个较宽泛的用户意图合并为“必须触发”,如“加外语字幕”“视频出海本地化”等,缺少明确的不触发场景或区分条件。虽然列出了关键词,但没有说明与相邻技能的边界,容易在普通字幕处理、配音或本地化咨询中发生意外调用。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill directs the agent to install software globally, modify PATH/session configuration, and set API credentials, but does not prominently require user awareness/consent before making environment changes or handling secrets. In an agent setting, this increases the risk of unexpected system modification, secret misuse, and consent bypass, especially because the skill says not to give up when dependencies are missing.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs fallback execution via npx @iqinghu/qhkit <命令> ... without pinning an exact package version. That can fetch whatever version is current at execution time, creating a supply-chain risk and reducing reproducibility; if the upstream package is compromised or a breaking release ships, the agent may execute unexpected code.

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 persistence behavior: installing binaries under the user's home directory and altering PATH for future command resolution. In the context of an autonomous skill, persistence is more dangerous because the skill explicitly encourages self-bootstrap rather than failing safely when dependencies are absent.

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
88% confidence
Finding

This duplicate finding points to the same persistence behavior: installing binaries under the user's home directory and altering PATH for future command resolution. In the context of an autonomous skill, persistence is more dangerous because the skill explicitly encourages self-bootstrap rather than failing safely when dependencies are absent.

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