Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently generates promotional poster images through the qhkit/LinkPix service, with disclosed installation, token, upload, and credit-use behavior.
Before installing, be comfortable with installing an npm CLI, configuring a qhkit token, sending supplied product images/prompts to the LinkPix/iqinghu service, and spending service credits. Prefer a controlled environment and review npm package provenance if supply-chain pinning matters to you.
The metadata says this skill 'must trigger' for a broad set of promotion-related requests, which can cause over-invocation of a tool-installing, network-using skill outside a narrowly intended scope. Overly aggressive auto-triggering increases the chance that the agent executes external CLI/setup steps when a user only asked for general advice, text drafting, or non-tool image planning.
The skill instructs fallback execution via npx @iqinghu/qhkit <命令> ... without pinning a specific version. That allows whatever package version is current at execution time to be fetched and run, which weakens supply-chain integrity and can unexpectedly introduce malicious or breaking code into the agent environment.
This is the same persistence issue duplicated by the scanner: extracting binaries under the home directory and altering PATH can leave durable modifications in the environment. In the context of an agent skill, these instructions normalize making lasting host changes as part of ordinary task fulfillment, increasing operational risk.
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:$PATH"
This is the same persistence issue duplicated by the scanner: extracting binaries under the home directory and altering PATH can leave durable modifications in the environment. In the context of an agent skill, these instructions normalize making lasting host changes as part of ordinary task fulfillment, increasing operational risk.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 section gives only positive examples and lacks boundaries or negative examples, making unintended invocation more likely. In this skill, that matters because invocation can cascade into package installation, environment modification, credential prompting, and outbound network use.