Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent read-only Douyin product research helper, but it tells agents to run an unpinned npm package at runtime while using an API key.
Review this before installing if your agent environment contains sensitive variables. The skill appears read-only and purpose-aligned, but it should ideally pin `socialdatax-skills` to an exact reviewed npm version or run in an isolated environment with only the needed `SOCIALDATAX_API_KEY` exposed.
The skill instructs the agent to execute npx -y socialdatax-skills@latest ..., which pulls and runs the newest package version at runtime instead of a fixed, reviewed release. If the npm package is compromised, typosquatted, or a malicious update is published, the agent could execute attacker-controlled code on the host with the user's environment variables, including SOCIALDATAX_API_KEY, available.
This command also relies on npx -y socialdatax-skills@latest, causing arbitrary remote code from the latest npm publication to be executed during skill use. In this skill's context, the danger is elevated because the command is meant to run in an agent environment and explicitly depends on a sensitive API key, so a compromised package could exfiltrate secrets or run local commands.
The third direct-call example repeats the same unsafe pattern of executing an unpinned npm package via npx. Because npx downloads and runs code on demand, any supply-chain compromise of the referenced package could immediately translate into code execution and possible credential theft or system compromise.
The file consistently specifies behavior and user-facing guidance only in Chinese, which can amount to a language/locale policy issue when no user choice is offered. The content does not indicate that the skill is region-restricted or that Chinese output is optional.
No suspicious patterns detected.
