Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent e-commerce image-generation helper, but users should understand it installs and runs an external CLI and sends product images/prompts to that service.
Before installing, confirm you are comfortable installing an npm CLI, storing or providing a Qinghu API token, and uploading product images/prompts to the qhkit service. Prefer reviewed or pinned package versions in controlled environments, and avoid adding PATH changes to shell startup files unless you want them to persist.
The activation description is extremely broad and mandates triggering for many generic image-generation requests across multiple commerce platforms. In an agent setting, overly broad triggers can cause the skill to intercept unrelated user requests and steer execution toward installing/running external tooling and collecting API credentials when a simpler or safer path would suffice.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which makes execution depend on whatever package version is current at runtime. That creates a supply-chain risk: a compromised or breaking upstream release could be fetched and executed in the agent environment without review.
This duplicate finding points to the same persistence behavior: unpacking software into a user-controlled directory and exporting that location into PATH, with guidance suggesting .bashrc changes for cross-command persistence. Such instructions normalize durable environment changes during skill execution, which is risky in shared or long-lived agent environments.
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:$PATH"
This duplicate finding points to the same persistence behavior: unpacking software into a user-controlled directory and exporting that location into PATH, with guidance suggesting .bashrc changes for cross-command persistence. Such instructions normalize durable environment changes during skill execution, which is risky in shared or long-lived agent environments.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 tells the agent to relay CLI messages and guidance in Chinese, effectively constraining user-facing output language without checking user preference. This is primarily a safety/usability issue: it can mislead or exclude users, and in security-relevant error cases it may reduce comprehension of installation, auth, or failure details.