Back to skill

Security audit

微博-热搜榜 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Weibo hot-search purpose is clear, but it also directs automatic software installation, unpinned package use, local PATH changes, and API-token configuration that users should review before installing.

Install only if you are comfortable letting the agent install or upgrade qhkit/Node tooling and configure a Qinghu API token locally. Prefer preinstalling a reviewed, pinned qhkit version yourself, avoid adding PATH changes to shell startup files unless needed, and confirm any paid qhkit call before use.

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
  • 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
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown explicitly lists 「追热点」 as a trigger, but this phrase is generic and could refer to many kinds of trend-following beyond querying the Weibo hot-search ranking. The file does not provide exclusion conditions or limiting context to reduce unintended invocation collisions.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s stated purpose is to fetch Weibo hot-search data, but it also instructs the agent to bootstrap the environment by downloading Node.js, globally installing packages, and configuring credentials. That significantly expands the attack surface and grants the skill authority to modify the host environment, turning a simple data-fetch skill into a software installation and configuration workflow.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which makes execution dependent on the latest package version available at runtime. That creates a supply-chain and reproducibility risk: a future compromised or incompatible release could be fetched and executed automatically.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
94% confidence
Finding

This finding is effectively the same persistent-install behavior duplicated by the scanner. The documented workflow installs binaries under the user home directory and encourages cross-command persistence, which expands the skill’s effect from a single query into durable host modification and creates opportunity for future command hijacking or unintended dependency trust.

Content

Scanner excerpt · SKILL.md (reported line 85)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
94% confidence
Finding

This finding is effectively the same persistent-install behavior duplicated by the scanner. The documented workflow installs binaries under the user home directory and encourages cross-command persistence, which expands the skill’s effect from a single query into durable host modification and creates opportunity for future command hijacking or unintended dependency trust.

Content

Scanner excerpt · SKILL.md (reported line 85)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
86% confidence
Finding

The instructions direct the agent to use only the domestic iqinghu.com flow and explicitly say not to guide users to the international site unless the user clearly states they use it. This imposes a locale-specific policy and account flow by default rather than offering a user choice or opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.