Back to skill

Security audit

亚马逊-卖家所属地分布 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its Amazon seller-origin analysis purpose, but it also directs automatic local installation and execution of third-party tooling in ways users should review first.

Install only if you trust the qhkit package and are comfortable with it being installed or configured locally. Prefer using a preinstalled or platform-managed qhkit, avoid unpinned npx or @latest upgrades in sensitive environments, and approve paid qhkit calls only after checking the estimated credits and requested marketplace/category parameters.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says the skill must trigger when the user says the listed examples "or提出同类需求时必须触发", which broadens activation beyond the explicit phrases. This leaves the boundary of what counts as a similar request unclear and could cause unintended invocation on adjacent Amazon-analysis queries.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill goes far beyond seller-origin analytics and includes extensive instructions to install Node, install npm packages, configure credentials, and modify the runtime environment. This meaningfully expands the attack surface by turning a data-query skill into a general environment bootstrapper capable of introducing new code and secrets-handling behaviors unrelated to the user’s analytic request.

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 execute an unpinned package via npx @iqinghu/qhkit, which fetches whatever version is current at runtime. That creates a supply-chain risk: a compromised latest release or dependency could execute arbitrary code in the agent environment, and the risk is amplified because this is presented as part of automatic environment bootstrap.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicated finding reflects the same persistence behavior: installing binaries into a user-controlled home directory and altering execution paths for future commands. Such stateful modification is unnecessary for the declared business function and creates lasting exposure if the installed toolchain is compromised or misused later.

Content

Scanner excerpt · SKILL.md (reported line 106)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
92% confidence
Finding

This duplicated finding reflects the same persistence behavior: installing binaries into a user-controlled home directory and altering execution paths for future commands. Such stateful modification is unnecessary for the declared business function and creates lasting exposure if the installed toolchain is compromised or misused later.

Content

Scanner excerpt · SKILL.md (reported line 106)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.