Security audit
Security checks for vulnerabilities and agentic risk
This skill is a narrow Shopee category lookup helper that discloses its external tool, paid API use, credential setup, and install steps, with some ordinary supply-chain and persistence considerations.
Before installing, confirm you trust the qhkit npm package and the iqinghu service, because the skill can install a CLI, store or use an API token, and make paid API calls after consent. Prefer an already managed Node/npm environment and review the estimated qhkit credits before authorizing calls.
The trigger text says the skill 'must' activate for broad, loosely bounded requests and similar needs, which increases the chance of inappropriate invocation. Over-broad triggering is dangerous here because this skill can lead the agent into installing software, configuring credentials, and making external paid API calls when the user's intent may only be informational or tangentially related.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows whatever package version is current at execution time to be fetched and run. In a security-sensitive agent context, this creates a supply-chain risk and undermines reproducibility, especially because the skill also promotes on-demand installation and execution of external tooling.
This duplicate finding points to the same behavior: unpacking a runtime into a user-owned directory and exporting it for later use. In an agent-driven workflow, persistent setup instructions are more dangerous than ordinary docs because they can normalize filesystem modifications and create lasting trust in externally fetched binaries.
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:$PATH"
This duplicate finding points to the same behavior: unpacking a runtime into a user-owned directory and exporting it for later use. In an agent-driven workflow, persistent setup instructions are more dangerous than ordinary docs because they can normalize filesystem modifications and create lasting trust in externally fetched binaries.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 invocation guidance provides positive examples but no exclusion criteria, so the agent lacks boundaries for when not to run the skill. In context, that can cause unnecessary external calls or environment-modifying setup for requests that merely mention Shopee categories without actually asking for this tool-driven lookup.
No suspicious patterns detected.