Back to skill

Security audit

亚马逊-商品历史趋势 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for Amazon product-history queries, but it asks agents to perform broad persistent setup and unpinned package installs without clear user approval boundaries.

Review before installing if you do not want an agent to install Node/npm packages, modify PATH setup, or configure a Qinghu API token. Prefer approving setup steps explicitly and pinning the qhkit package version where possible.

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
91% confidence
Finding

The description says the skill '必须触发' when the user asks the listed examples '或提出同类需求时', but it does not define what counts as a similar request. This creates an ambiguous activation scope for a manifest/markdown file and could cause unintended invocation on loosely related Amazon analytics questions.

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 stated purpose is querying Amazon product-history data, but it also instructs broad environment bootstrapping: installing Node.js, globally installing npm packages, and configuring credentials. That expands the trust boundary significantly and encourages arbitrary software installation on the host, which is dangerous in an agent context because it changes system state far beyond the user’s original request.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
83% confidence
Finding

The skill tells the agent to execute npx @iqinghu/qhkit without pinning a specific version. That can pull whatever the latest package is at execution time, creating a supply-chain risk and making behavior non-reproducible if the upstream package is compromised or changes unexpectedly.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
90% confidence
Finding

This duplicate finding identifies the same persistence behavior: unpacking binaries into a user-controlled directory and exporting a modified PATH. In an agent setting, persistence increases the blast radius because it can affect later sessions and enable continued execution of externally fetched tooling beyond the immediate task.

Content

Scanner excerpt · SKILL.md (reported line 113)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 identifies the same persistence behavior: unpacking binaries into a user-controlled directory and exporting a modified PATH. In an agent setting, persistence increases the blast radius because it can affect later sessions and enable continued execution of externally fetched tooling beyond the immediate task.

Content

Scanner excerpt · SKILL.md (reported line 113)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
84% confidence
Finding

These lines instruct the agent to direct users to the China-site account flow and explicitly avoid international-site guidance unless the user clearly states they use the international version. This imposes a locale-specific workflow by default rather than offering a user choice or opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.