Back to skill

Security audit

小红书-种草码生成 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Qinghu/RedNote publishing-code integration, with notable but purpose-aligned install and token setup risks.

Before installing, confirm you trust the qhkit package and Qinghu service, approve any Node/npm installation or upgrade, and decide whether the token should be stored in qhkit config or supplied through an environment variable. Check the site setting before overwriting an existing international account configuration, and expect paid qhkit calls to consume Qinghu credits after you authorize them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill goes far beyond its stated purpose of generating a RedNote publish code by directing installation of Node.js, global package installation, upgrades, and environment bootstrapping. Expanding scope this way increases attack surface and can cause the agent to modify the host system in ways the user did not explicitly request or expect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to install software and configure credentials, including setting API tokens, without a prominent host-modification and secret-handling warning. This is dangerous because it can lead to persistent system changes and sensitive credential exposure or misuse under the guise of a routine content-generation task.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill instructs the agent to run npx @iqinghu/qhkit without pinning an exact version, which allows whatever package version is current at execution time to be fetched and executed. That creates a supply-chain risk and makes behavior non-reproducible, especially because this package is then used to access credentials and external services.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This finding is substantively the same persistence issue: the instructions establish a user-local runtime and alter execution paths in a way that can outlive the session. Persistent environment modification is risky because it changes future command resolution and broadens the consequences of any compromised or misconfigured dependency.

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
88% confidence
Finding

This finding is substantively the same persistence issue: the instructions establish a user-local runtime and alter execution paths in a way that can outlive the session. Persistent environment modification is risky because it changes future command resolution and broadens the consequences of any compromised or misconfigured dependency.

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
87% confidence
Finding

The skill forces a China-site configuration unless the user explicitly states otherwise, overriding user/environment context and steering credentials toward a specific service endpoint. In practice, this can cause accidental credential misuse, policy mismatches, or data routing to an unintended locale, which is especially sensitive for account-bound API operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.