Security audit
Security checks for vulnerabilities and agentic risk
The skill performs the advertised Shopee brand-ranking lookup, but its runtime instructions also tell the agent to install tools, alter the user environment, and configure API credentials, which should be reviewed before use.
Install only if you are comfortable with qhkit being installed or upgraded, Node possibly being added under your home directory, PATH/config changes, and a Qinghu API token being configured. Prefer a pre-provisioned qhkit installation and scoped token, confirm any ambiguous request before invoking the skill, and review estimated Qinghu credit cost before paid calls.
The description says matching user requests 'must trigger' the skill and includes broad commerce-related keywords, which can cause automatic invocation without clear user intent. In this skill, unintended activation is more dangerous because invocation may lead to paid external calls and, per the document, even environment setup or credential workflows.
The 'when to trigger' examples are generic phrases like '最近飙升的品牌' and '头部品牌有哪些' without clear platform, scope, or data-source boundaries. This can misroute unrelated requests into this skill, leading to unnecessary external calls, billing, or use of the wrong tool for the user's intent.
The skill goes far beyond describing a ranking query and instructs the agent to install software, modify PATH, configure tokens, and bootstrap runtime dependencies on the host. This expands the attack surface from a narrow data-query skill into host-environment modification, enabling persistence, credential handling, and execution of newly downloaded code from external sources.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows whatever package version is current at execution time to be fetched and run. In a skill context, this increases supply-chain risk and makes behavior non-reproducible, especially because the package is then used to access external services and credentials.
This duplicated finding identifies the same persistence behavior: extracting software into the user's home directory and altering PATH for future command execution. In context, this meaningfully increases risk because the skill is nominally for data lookup, yet it directs durable host modification and execution of downloaded tooling.
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:$PATH"
This duplicated finding identifies the same persistence behavior: extracting software into the user's home directory and altering PATH for future command execution. In context, this meaningfully increases risk because the skill is nominally for data lookup, yet it directs durable host modification and execution of downloaded tooling.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
These lines explicitly direct access to API keys and instruct modifying credential configuration with qhkit config set --token <密钥> --env prod or environment variables. A skill that solicits, sets, or overwrites credentials on the host can facilitate credential exfiltration, misuse of privileged tokens, or accidental replacement of existing secure configuration.
No suspicious patterns detected.