Security audit
Security checks for vulnerabilities and agentic risk
This skill has a coherent paid profile-lookup purpose, but its self-install and credential setup instructions give the agent more environment-changing authority than the lookup task needs.
Review before installing. Use it only if you are comfortable with qhkit, paid Qinghu credits, and providing a Qinghu API token. Prefer a preinstalled, trusted qhkit/Node environment and avoid letting the skill automatically install Node, run unpinned latest packages, or persist credentials unless you understand where they are stored.
The trigger language says the skill 'must' activate for broadly similar requests, creating a high chance of over-invocation outside the user's precise intent. In this skill, over-triggering is more dangerous because invocation can lead to paid external calls and environment-changing setup steps.
The listed phrases are short and generic enough to overlap with ordinary conversation, which can cause accidental triggering. Because this skill can prompt external tool usage and billing, ambiguous trigger phrases increase the risk of unintended actions and data access.
For a read-only profile lookup skill, directing the agent to install Node.js, install npm packages globally, download binaries, and modify PATH substantially exceeds the minimum required capability. This expands the attack surface from a simple data query into arbitrary environment modification and code execution, which is dangerous if the skill content is adversarial or the package source is compromised.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows execution of whatever package version is current at runtime. In a skill that may auto-bootstrap tooling, this creates supply-chain risk and makes behavior non-reproducible if a compromised or breaking upstream release is published.
This duplicate finding highlights the same persistence behavior: unpacking software into the user's home directory and exporting a new PATH entry. Even if framed as convenience, it grants the skill lasting influence over the session environment, which is disproportionate to the stated purpose and increases post-execution risk.
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:$PATH"
This duplicate finding highlights the same persistence behavior: unpacking software into the user's home directory and exporting a new PATH entry. Even if framed as convenience, it grants the skill lasting influence over the session environment, which is disproportionate to the stated purpose and increases post-execution risk.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 persistent credential configuration via qhkit config set --token or QHKIT_TOKEN, which writes secrets into the environment or tool config for a task that only claims to fetch profile data. Persisting credentials from within a skill increases risk of secret exposure, reuse across sessions, and unauthorized downstream access beyond the immediate user-approved operation.
No suspicious patterns detected.