Back to skill

Security audit

亚马逊-类目需求趋势 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate Amazon analytics purpose, but it also tells the agent to install/update host tooling and configure persistent API credentials as part of normal use.

Install only if you are comfortable letting the skill install or update Node/qhkit tooling and store a Qinghu API token locally. Prefer a sandbox or preinstalled, pinned qhkit version, review any paid-call prompt before approving, and avoid giving it broader shell or account access than needed.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says the skill must trigger when the user says the listed examples "or提出同类需求时", which does not clearly bound what counts as a similar request. That ambiguity can cause unintended activation for loosely related category-analysis questions without explicit exclusion conditions or negative examples.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This analytics skill contains extensive instructions to install Node/qhkit, modify host configuration, and set persistent API credentials on the host. For a category-demand-trend lookup skill, that is unnecessarily invasive and expands the attack surface from simple data retrieval to arbitrary software installation, credential handling, and environment manipulation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows execution of whatever version is current at invocation time. That creates supply-chain and reproducibility risk, especially because this skill also encourages host-side installation and execution of external tooling.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This duplicate finding identifies the same persistent installation behavior: extracting Node into a user directory and exporting a modified PATH. Such persistence can outlive the session and changes the trust boundary of the host, which is disproportionate to the skill's stated analytics purpose.

Content

Scanner excerpt · SKILL.md (reported line 102)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
95% confidence
Finding

This duplicate finding identifies the same persistent installation behavior: extracting Node into a user directory and exporting a modified PATH. Such persistence can outlive the session and changes the trust boundary of the host, which is disproportionate to the skill's stated analytics purpose.

Content

Scanner excerpt · SKILL.md (reported line 102)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.