Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to support legitimate Amazon market research, but it can install or upgrade tools and configure API credentials on the user's machine, so it needs Review before installation.
Install only if you trust the qhkit package and Qinghu account workflow. Prefer a pre-provisioned qhkit/Node environment, avoid unpinned npx or @latest upgrades, and do not let the agent store or overwrite API tokens unless you explicitly intend that.
The trigger description includes broad catch-all wording such as "or similar needs must trigger," which can cause the skill to activate outside narrowly intended contexts. Over-broad invocation is dangerous here because the skill contains installation, configuration, and paid-tool usage instructions, so accidental activation can lead to unnecessary host changes or credential workflows.
The markdown instructs the agent to translate user-provided category keywords from Chinese into the marketplace language before querying, assuming Chinese as the default user language. This imposes a language-specific workflow without offering the user a language choice or clarifying that the behavior is optional.
This market-analysis skill goes beyond its stated purpose by directing the agent to install Node.js, install packages globally, and bootstrap tooling on the host. Expanding from data retrieval into host modification materially increases attack surface and enables unreviewed code execution and persistent environment changes unrelated to the user’s analytical request.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which permits execution of whatever package version is current at runtime. That creates a supply-chain risk: a malicious or compromised future release could be fetched and executed automatically in the agent environment.
This duplicate persistence finding points to the same behavior: extracting software into a user-controlled directory and altering PATH for future use. Even with checksum verification, the skill is still directing durable host modification unrelated to the immediate analytical result, which increases the blast radius of any compromise or mistake.
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:$PATH"
This duplicate persistence finding points to the same behavior: extracting software into a user-controlled directory and altering PATH for future use. Even with checksum verification, the skill is still directing durable host modification unrelated to the immediate analytical result, which increases the blast radius of any compromise or mistake.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 skill instructs the agent to set API tokens via qhkit config set or environment variables, which is a credential-handling and account-configuration action outside the scope of simple market screening. This can lead the agent to request, store, or overwrite secrets in the host environment, creating risk of credential exposure, misuse, and unintended account changes.
No suspicious patterns detected.