Back to skill

Security audit

Shopee-类目长期趋势 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Shopee trend-query integration, with some setup and credential-handling risks users should understand before use.

Install only if you are comfortable with qhkit, npm-based setup, and providing a Qinghu API token. Prefer a preinstalled or pinned qhkit version, review any npm or Node installation before allowing it, and approve paid calls because the skill can consume Qinghu credits.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill claims to only perform Shopee trend queries, but it also directs host-environment installation, configuration, and credential setup. This is a scope expansion that increases attack surface and can lead an agent to make host changes unrelated to the user-visible analytics task.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation includes package installation, runtime setup, downloads, and PATH modification even though the stated purpose is category trend analysis. Those host-level actions create unnecessary execution and persistence paths that could be abused if the package source or instructions are compromised.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
81% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version. That can cause nondeterministic execution and supply-chain risk because a future or compromised package version could be fetched and run at invocation time.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
93% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking software into the user's home directory and altering executable resolution. In the context of a data-query skill, such persistence is unnecessary and increases the blast radius of supply-chain or misuse scenarios.

Content

Scanner excerpt · SKILL.md (reported line 99)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
93% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking software into the user's home directory and altering executable resolution. In the context of a data-query skill, such persistence is unnecessary and increases the blast radius of supply-chain or misuse scenarios.

Content

Scanner excerpt · SKILL.md (reported line 99)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
94% confidence
Finding

The skill instructs the agent to set API tokens and environment variables on the host, which exceeds the stated analytics function and touches sensitive secret handling. This can expose credentials to logs, shell history, or unintended reuse by other processes and sessions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.