Security audit
Security checks for vulnerabilities and agentic risk
The skill appears intended for product mockups, but it tells the agent to install or upgrade external tooling and configure service credentials in ways users should review first.
Install only if you are comfortable using LinkPix/qhkit, uploading mockup source images to that service, and letting the agent manage npm tooling. Prefer a preinstalled or pinned qhkit version, avoid putting tokens directly in shell history where possible, and review any proposed Node/npm/PATH changes before allowing them.
The trigger description says the skill 'must' activate for broad categories of product-mockup requests, which can cause over-invocation on common user prompts. Overly broad mandatory triggering is dangerous because it can unexpectedly route benign image-editing requests into a skill that performs installation, configuration, and external service usage.
The trigger section provides only positive examples and lacks clear boundaries for when the skill should not run. In context, that matters because the skill includes side-effectful setup and credential steps, so ambiguity increases the chance of unnecessary execution and user surprise.
The documented behavior goes well beyond generating a mockup: it instructs the agent to bootstrap Node, globally install packages, modify PATH, and troubleshoot environment setup. That materially expands the skill's operational scope from image generation to host modification, creating unnecessary attack surface and opportunities for persistence or unintended system changes.
The skill instructs use of npx @iqinghu/qhkit without pinning a version, which allows the fetched package version to drift over time and can expose users to supply-chain risk if a newer malicious or compromised release is published. In a skill that already encourages on-demand installation and execution, this increases the chance of executing unreviewed code from the registry.
This duplicate finding identifies the same persistent installation behavior: extracting Node into the user's home directory and exporting a modified PATH. That behavior is risky in a skill meant for mockup generation because it normalizes durable host modification as part of routine task execution.
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:$PATH"
This duplicate finding identifies the same persistent installation behavior: extracting Node into the user's home directory and exporting a modified PATH. That behavior is risky in a skill meant for mockup generation because it normalizes durable host modification as part of routine task execution.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 users to obtain and configure a long-lived API token via command line or environment variable, which introduces credential handling into a task that should ideally use platform-managed secrets. This creates risk of credential leakage through shell history, logs, screenshots, or reuse in the wrong environment.