Back to skill

Security audit

AI电商视频广告 | 视频广告素材 | 信息流广告 | 广告视频生成 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill’s video-ad generation purpose is coherent, but it gives broad self-install and upgrade instructions that can persistently change the user environment without clear consent controls.

Review this skill before installing if you do not want agents to install or upgrade Node/npm tooling, run unpinned npx commands, store a QHKit token, upload local product images, or spend Qinghu credits. Prefer a preinstalled, pinned qhkit version and confirm costs before any generate command.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description says this skill '必须触发' for broad categories like ad videos and social media video assets, creating an overly aggressive routing rule. In an agent setting, mandatory broad invocation can cause unintended tool use, external network calls, package installation, and billing actions for ordinary user requests that may not require this skill.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs falling back to npx @iqinghu/qhkit <命令> ..., which fetches and executes a package at runtime without a pinned version. That creates a supply-chain risk: a compromised upstream package, malicious new release, or dependency takeover could lead to arbitrary code execution in the agent environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
82% confidence
Finding

This duplicated finding points to the same persistent installation behavior: unpacking Node into a user directory and exporting a modified PATH, with nearby instructions encouraging persistence across sessions. In an agent context, persistent host changes expand the blast radius from a single run to future sessions and workflows.

Content

Scanner excerpt · SKILL.md (reported line 55)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
82% confidence
Finding

This duplicated finding points to the same persistent installation behavior: unpacking Node into a user directory and exporting a modified PATH, with nearby instructions encouraging persistence across sessions. In an agent context, persistent host changes expand the blast radius from a single run to future sessions and workflows.

Content

Scanner excerpt · SKILL.md (reported line 55)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
87% confidence
Finding

The "何时触发" section gives two example requests, including "给投放准备视频素材" and a general condition about producing multiple platform variants. This describes broad situations but does not clearly distinguish this skill from other video-generation skills, increasing the chance of overlapping or accidental activation.

Content

No source excerpt is available for this finding.