Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed 1688 reverse-image-search helper that uses a paid Qinghu/qhkit integration with some installation and consent cautions but no artifact-backed malicious behavior.
Install only if you are comfortable giving qhkit a Qinghu API token, sending public product image URLs to the Qinghu/1688 service, and spending Qinghu credits after the agent asks for approval. Prefer a pinned or already-installed qhkit version when possible, and review any npm or Node installation commands before letting an agent run them.
The frontmatter description says the skill 'must trigger' for broad, loosely defined requests related to image-based sourcing. Overbroad mandatory triggering can cause the agent to invoke an external paid/networked tool in situations where user intent is ambiguous, increasing the chance of unauthorized actions, privacy leakage, or unnecessary spend.
The markdown trigger section repeats broad activation criteria like '找货源/找工厂/找供应链', which overlap with many general commerce-assistance requests. In context, this can steer the agent into invoking the skill beyond its narrow capability, potentially disclosing user-provided image URLs to third parties and incurring charges without sufficiently specific consent.
The skill instructs fallback execution via npx @iqinghu/qhkit without pinning an exact version. That makes runtime behavior depend on whatever package version is current at execution time, increasing supply-chain risk and reducing reproducibility if a compromised or breaking release is published.
This duplicate finding points to the same persistence behavior: unpacking binaries into a user-controlled persistent directory and altering PATH for future commands. Even though checksum verification is suggested, persistence itself is risky in an agent skill because it encourages durable host modification beyond the requested operation.
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:$PATH"
This duplicate finding points to the same persistence behavior: unpacking binaries into a user-controlled persistent directory and altering PATH for future commands. Even though checksum verification is suggested, persistence itself is risky in an agent skill because it encourages durable host modification beyond the requested operation.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
No suspicious patterns detected.