Security audit
Security checks for vulnerabilities and agentic risk
The skill matches its advertised Amazon keyword lookup purpose, but it also directs host package installation, upgrades, PATH changes, and paid-service credential setup that users should review before installing.
Review this skill before installing if you do not want an agent to install or upgrade Node/npm tooling, store a Qinghu API token, or run paid qhkit calls. Prefer a preinstalled, pinned qhkit version and approve credential setup and credit-spending calls explicitly.
The manifest says the skill must trigger when the user makes the listed requests 'or提出同类需求', which broadens activation beyond the enumerated examples without defining boundaries. This ambiguity can cause unintended invocation for loosely related Amazon keyword-analysis requests or everyday phrasing adjacent to the examples.
The skill goes far beyond describing how to query ASIN keyword data: it instructs the agent to install Node, install global packages, configure API credentials, modify PATH, and remediate environment issues on the host. This materially expands the skill's privileges and attack surface, enabling host modification and credential handling unrelated to the core user request.
The skill instructs using npx @iqinghu/qhkit without pinning an exact version, which allows retrieval of whatever package version is current at execution time. In a skill context that also directs installation and execution of external tooling, this creates supply-chain risk and undermines reproducibility and reviewability.
This duplicate finding reflects the same risky behavior: the skill prescribes local installation into a user-controlled directory and environment modification to make the new runtime active. Even with checksum verification, the core issue is unauthorized persistence and host-state changes outside the narrow scope of keyword lookup.
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:$PATH"
This duplicate finding reflects the same risky behavior: the skill prescribes local installation into a user-controlled directory and environment modification to make the new runtime active. Even with checksum verification, the core issue is unauthorized persistence and host-state changes outside the narrow scope of keyword lookup.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
The trigger example '反查竞品关键词' is broad enough to overlap with multiple keyword-analysis workflows, not just ASIN traffic-keyword reverse lookup. Without qualifiers like required platform, ASIN context, or tool scope, it may activate this skill when a different competitor-keyword skill would be more appropriate.
No suspicious patterns detected.