Back to skill

Security audit

抖音-热搜榜 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says, but it also tells the agent to install and configure external tooling in ways that can persist beyond the immediate query.

Install only if you are comfortable allowing the skill to install or upgrade qhkit/Node tooling and configure a Qinghu API token on your machine. Prefer preinstalling and pinning the qhkit version yourself, avoid npx/@latest execution, and approve paid qhkit calls only after the quoted Qinghu credit cost is shown.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest says the skill 'must trigger' when users ask the listed examples 'or similar needs', which creates an open-ended activation condition. Without explicit exclusions or narrower scope, this can overlap with general requests about trends or content ideas and cause unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger example '蹭热点选题' is not specific to Douyin hot-search retrieval and could apply to many ordinary brainstorming or marketing conversations. Because the skill is narrowly for querying a specific Douyin ranking tool, this phrase risks accidental activation outside the intended context.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill's purpose is to fetch Douyin hot-search data, but it contains broad environment-bootstrap instructions including installing Node, globally installing packages, setting tokens, and modifying runtime configuration. Expanding a data-query skill into software installation and environment modification increases attack surface and can cause the agent to perform privileged or persistent actions unrelated to the user's immediate request.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact package version. Because npx fetches whatever version is current at execution time, this creates a supply-chain risk where a compromised or incompatible upstream release could be executed in the host environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This duplicate finding points to the same persistence behavior: downloading and unpacking executables into the user's home directory and altering PATH. In the context of a simple data-retrieval skill, persistent environment mutation is unnecessary and dangerous because it can affect later sessions and trust boundaries.

Content

Scanner excerpt · SKILL.md (reported line 86)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
95% confidence
Finding

This duplicate finding points to the same persistence behavior: downloading and unpacking executables into the user's home directory and altering PATH. In the context of a simple data-retrieval skill, persistent environment mutation is unnecessary and dangerous because it can affect later sessions and trust boundaries.

Content

Scanner excerpt · SKILL.md (reported line 86)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

Static analysis

No suspicious patterns detected.