Back to skill

Security audit

B站-UP主投稿视频 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the advertised Bilibili creator-video lookup, but it also authorizes installing or updating CLI software, Node, and local token configuration, so users should review it before installing.

Install only if you are comfortable with the agent setting up qhkit/Node and configuring a Qinghu API token on your machine. Prefer reviewing or performing the setup yourself, pinning package versions where possible, and confirming paid qhkit calls before allowing data retrieval.

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
95% confidence
Finding

The manifest says the skill must trigger not only for two example phrases, but also for unspecified 'similar requests'. That creates an ambiguous activation boundary and can cause unintended invocation for loosely related requests about Bilibili creators or video stats.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill goes far beyond its declared purpose of querying Bilibili creator videos by directing the agent to install Node, install packages globally, configure tokens, and modify the runtime environment. This expands the attack surface substantially and can lead to unreviewed software execution, credential handling, and host modification in response to a simple data-query request.

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 a specific version, which allows whatever package version is current at execution time to be fetched and run. In a skill context, this creates a supply-chain and reproducibility risk because future package changes or a compromised upstream release could alter behavior unexpectedly.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
90% confidence
Finding

This duplicate finding points to the same persistence behavior: installing binaries under the home directory and changing PATH for future command execution. In context, the persistence is more dangerous because the skill's advertised function is only a narrow data lookup, yet it authorizes durable system modification unrelated to that business purpose.

Content

Scanner excerpt · SKILL.md (reported line 89)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
90% confidence
Finding

This duplicate finding points to the same persistence behavior: installing binaries under the home directory and changing PATH for future command execution. In context, the persistence is more dangerous because the skill's advertised function is only a narrow data lookup, yet it authorizes durable system modification unrelated to that business purpose.

Content

Scanner excerpt · SKILL.md (reported line 89)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 file instructs the agent to require the domestic CN site and to avoid international-site guidance unless the user clearly says they use AutoAGC. This imposes a locale/site constraint by default rather than offering the user a choice or making the constraint explicit up front as an opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.