Back to skill

Security audit

小红书-博主主页笔记 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill’s main RedNote data-fetching purpose is clear, but it also tells agents to install and upgrade tooling, download Node, change PATH, and store API credentials with limited user control.

Review before installing. Use this skill only if you are comfortable with qhkit accessing a paid Qinghu account, storing an API token, and making local tooling changes. Prefer preinstalling and pinning qhkit yourself, and approve paid calls only after checking the estimate.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says requests like pulling all a creator’s notes or doing account benchmarking 'must trigger,' and includes broad keywords that can overlap with general analysis tasks. This increases the chance of unintended invocation, which is more dangerous here because invocation can lead to paid external calls and environment-changing setup behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The trigger examples are short and broad, especially '对标账号作品分析', which can overlap with multi-step competitive analysis outside the skill’s narrow stated function. Ambiguous triggers can cause the skill to run in situations where the user did not intend this specific paid data collection flow.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill goes beyond its stated purpose of fetching RedNote creator notes by instructing the agent to install Node, install or upgrade CLI software, and persistently configure API credentials. In an agent setting, these actions expand the trust boundary, modify the host environment, and may expose secrets or create lasting changes unrelated to the user’s immediate data request.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The skill instructs using npx @iqinghu/qhkit without pinning a specific version, which causes execution of whatever package version is current at runtime. That creates a supply-chain risk and undermines reproducibility, especially because the package is used to access external services and handle authentication.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
91% confidence
Finding

This duplicate finding points to the same persistence behavior: extracting binaries into the user profile and exporting a modified PATH. Even if partly framed as session-local, the instructions also encourage durable installation patterns and therefore exceed the minimum privileges needed for the skill’s purpose.

Content

Scanner excerpt · SKILL.md (reported line 88)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 points to the same persistence behavior: extracting binaries into the user profile and exporting a modified PATH. Even if partly framed as session-local, the instructions also encourage durable installation patterns and therefore exceed the minimum privileges needed for the skill’s purpose.

Content

Scanner excerpt · SKILL.md (reported line 88)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.