Security audit
Security checks for vulnerabilities and agentic risk
This Amazon competitor-research skill is coherent, but it can automatically install tools, change local configuration, and store/use an API token beyond a simple data lookup.
Review this before installing if you do not want skills to install Node/npm packages, change local shell configuration, or store qhkit API credentials. Use it only in an environment where qhkit is trusted, prefer a preinstalled/pinned version, and confirm paid calls and any setup steps explicitly.
The frontmatter description says the skill 'must trigger' for broad comparable requests and includes expansive keyword matching, which can cause over-invocation. In practice, that increases the chance an agent routes unrelated user prompts into a paid external tool or into the risky setup/install flow described later in the file.
The trigger section lists example phrases but lacks boundaries, disambiguation rules, and explicit non-trigger cases. Because this skill is user-invocable and later instructs installation and paid calls, weak activation constraints make accidental or excessive invocation more dangerous than in a purely local read-only skill.
This competitor-query skill goes far beyond data lookup by directing the agent to install Node, install global packages, download binaries, set tokens, and modify local configuration. Those actions expand the skill from scoped tool use into host modification and credential handling, materially increasing the attack surface if the skill is invoked automatically or in a sensitive environment.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which makes execution depend on whatever package version is current at run time. That creates supply-chain and reproducibility risk: a later compromised or incompatible release could be fetched and executed in the agent environment.
This duplicated finding points to the same persistence behavior: extracting Node into the user home directory and exporting a modified PATH. Even with checksum verification, persisting executables and environment changes from a data-query skill is over-privileged and can influence future agent behavior or create durable footholds for later misuse.
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:$PATH"
This duplicated finding points to the same persistence behavior: extracting Node into the user home directory and exporting a modified PATH. Even with checksum verification, persisting executables and environment changes from a data-query skill is over-privileged and can influence future agent behavior or create durable footholds for later misuse.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.