Back to skill

Security audit

视频号-合集列表 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill has a clear data-query purpose, but it asks agents to install or update tooling and configure an API token in ways users should review first.

Review this skill before installing if you do not want an agent to modify your local Node/npm environment or configure a Qinghu API token. Prefer a preinstalled, pinned qhkit version and provide credentials through a controlled secret store or per-session environment variable. Confirm paid Qinghu credit usage before any call.

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
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description specifies only Chinese trigger examples and says the skill 'must trigger' for similar requests, but it does not offer any user language/locale choice. This creates a natural-language locale policy concern because the skill appears to enforce a specific language context without opt-in or justification.

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 documented behavior goes far beyond querying collection data: it tells the agent to install Node.js, globally install packages, and upgrade tooling. That expands the skill from a narrow data-retrieval capability into environment modification and software management, increasing blast radius if the instructions are followed automatically.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows resolution of whatever package version is current at execution time. In an agent context this creates supply-chain risk and undermines reproducibility, especially because the package is then trusted to perform external calls and handle credentials.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
91% confidence
Finding

This duplicate finding identifies the same persistence behavior: unpacking Node into a user-controlled directory and exporting a modified PATH, with optional persistence across sessions. In context, the danger is not the specific package alone but the skill encouraging durable host changes unrelated to its narrow business purpose.

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
91% confidence
Finding

This duplicate finding identifies the same persistence behavior: unpacking Node into a user-controlled directory and exporting a modified PATH, with optional persistence across sessions. In context, the danger is not the specific package alone but the skill encouraging durable host changes unrelated to its narrow business purpose.

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

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs persistent credential configuration via qhkit config set --token or QHKIT_TOKEN. This introduces secret-handling and storage behavior unrelated to the stated query function, and can cause long-lived credentials to be written into the host environment where other processes or later sessions may access them.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.