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 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

The skill appears consistent with its stated purpose of generating LinkPix/qhkit advertising videos, with disclosed setup, API-token use, pricing checks, and delivery steps.

Before installing, confirm you want this skill to install or run qhkit from npm and store or use a qhkit API token for the LinkPix service. For bulk generation, verify the estimate before approving work that consumes account credits, and avoid making PATH or shell-profile changes unless you want the tooling to persist across sessions.

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
  • 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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The metadata says this skill 'must trigger' for broad, common ad-video requests. Overly broad mandatory triggering can cause the agent to invoke the skill in situations where it is not necessary, increasing the chance of unnecessary external tool use, package installation, and token-handling for ordinary user requests.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The skill recommends falling back to npx @iqinghu/qhkit <命令> ... without pinning a specific package version. That allows execution of whatever version is current at invocation time, increasing supply-chain risk and making behavior non-deterministic if a malicious or compromised release is published.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
79% confidence
Finding

This duplicated finding identifies the same persistence behavior: unpacking software into the user's home directory and advising PATH persistence across commands or via ~/.bashrc. Even with checksum verification, the pattern creates lasting environmental changes that may outlive the task and expand risk if the toolchain is later abused.

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
79% confidence
Finding

This duplicated finding identifies the same persistence behavior: unpacking software into the user's home directory and advising PATH persistence across commands or via ~/.bashrc. Even with checksum verification, the pattern creates lasting environmental changes that may outlive the task and expand risk if the toolchain is later abused.

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

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instructions explicitly require using domestic-site key guidance and note that CLI messages are already user-facing Chinese, implying a fixed Chinese-language interaction pattern. The file does not offer the user a language choice or document a justified locale restriction, which violates the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The '何时触发' section gives only broad examples like preparing video assets for ads or bulk-producing platform variants. It does not clarify edge cases or when related requests should route to other skills, which can cause unintended invocation overlap.

Content

No source excerpt is available for this finding.