Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a read-only ecommerce copywriting helper, but it runs a mutable npm package at runtime with an API key available, so users should review that supply-chain risk before installing.
Install only if you are comfortable trusting the current npm package each time it runs. Prefer a pinned, reviewed `socialdatax-skills` version or a controlled environment with minimal filesystem and environment-variable access; keep the API key scoped and rotate it if you suspect exposure.
The description and usage instructions are written as if the skill operates in Chinese by default, and there is no opt-in or alternative language/locale option described. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly documented and justified.
The skill instructs agents to execute npx -y socialdatax-skills@latest ..., which fetches and runs the newest package version at execution time instead of a reviewed, fixed release. This creates a software supply-chain risk: if the package is compromised, updated maliciously, or a breaking release is published, the agent may execute attacker-controlled code while holding environment access including SOCIALDATAX_API_KEY.
This command again uses npx -y socialdatax-skills@latest, causing dynamic retrieval and execution of whatever version is current at runtime. In an agent setting, that exposes the host to supply-chain compromise and arbitrary code execution through an unpinned package.
Using npx with @latest for this product-detail invocation means the agent trusts a mutable upstream package each time the skill runs. Because the package executes locally, a malicious or compromised release could access files, environment variables, or network resources available to the agent.
The command references an unpinned package version via @latest, so behavior and code origin are not stable or auditable. This is particularly risky because the skill explicitly expects an API key in the environment, which a malicious package could exfiltrate.
This search command also executes socialdatax-skills@latest, inheriting the same package substitution and upstream compromise risks as the other examples. Even though the skill is described as read-only, the package itself would still run arbitrary JavaScript on the host before performing any read-only business action.
The final CLI example repeats execution of a floating @latest package, which undermines reproducibility and opens a direct supply-chain execution path. In environments where agents can run shell commands, this can lead to host compromise or credential theft if the package is ever poisoned.
No suspicious patterns detected.
