Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a real 1688 image-generation skill, but it needs Review because it asks for an API key in chat and relies on unpinned remote package installs.
Install only if you trust qhkit/iqinghu and are comfortable uploading product images to that service. Do not paste API keys into chat; configure the token yourself through an environment variable or local CLI command. Review estimated credit costs and generated parameters before approving any generate command, and prefer pinned package versions or an isolated environment for installation.
The description says the skill 'must' trigger when users ask for 1688 product images and is written as a China-market workflow, but it does not explicitly frame this as a region-specific skill boundary or offer any language/locale opt-in. Under the policy, forcing a specific language/locale context without user choice can be a natural-language policy violation.
The skill instructs use of npx @iqinghu/qhkit without pinning a package version, which makes execution depend on whatever version is current at runtime. In an agent context this creates a supply-chain risk: a compromised or breaking upstream release could be fetched and executed automatically with the agent's privileges.
This duplicate finding points to the same behavior: unpacking Node into a user-writable directory and exporting it into PATH. In an agent setting, such persistence is riskier than in ordinary documentation because the instructions are meant to be acted on automatically, potentially altering the host environment beyond the immediate task.
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:$PATH"
This duplicate finding points to the same behavior: unpacking Node into a user-writable directory and exporting it into PATH. In an agent setting, such persistence is riskier than in ordinary documentation because the instructions are meant to be acted on automatically, potentially altering the host environment beyond the immediate task.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 explicitly tells the agent to ask the user to send an API key in chat and then configure the CLI with it. Collecting secrets through chat is dangerous because chat transcripts may be logged, retained, exposed to other tools, or mishandled by the agent, turning a normal setup flow into a credential-exposure risk.
The fallback command npx --yes sharp-cli also executes an unpinned package from the registry, allowing silent retrieval of the latest published code. Because this path is invoked during error handling and local file processing, it expands the attack surface and could lead to arbitrary code execution if the package or dependency chain is compromised.