Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a read-only ecommerce reply helper, but it tells agents to run an unpinned external npm package at runtime.
Install only if you are comfortable letting the agent run npm code from SocialDataX with your `SOCIALDATAX_API_KEY`. Prefer a pinned reviewed package version or a preinstalled trusted CLI, and use a constrained environment for shell/network execution.
The skill content is written as if interaction and output are expected in Chinese, and it does not state that the user may choose another language. Because SQP-3 covers language or locale policy violations, a skill that effectively fixes one language without opt-in should be flagged.
The skill invokes npx -y socialdatax-skills@latest, which fetches and executes the newest package version at runtime without pinning to a known-good release. If the upstream package is compromised, typosquatted, or a malicious update is published, an agent following this skill could execute attacker-controlled code in its local environment.
This command again uses npx -y socialdatax-skills@latest, causing unpinned remote code execution every time the skill is used. In agent environments with shell access and secrets such as SOCIALDATAX_API_KEY, a compromised package update could run arbitrary commands, exfiltrate credentials, or tamper with outputs.
Using npx with an unpinned @latest package for the XHS command introduces the same supply-chain risk: the actual code executed is determined at runtime by the current registry state, not by a reviewed artifact. That makes the skill vulnerable to malicious upstream releases or dependency compromise.
The final direct-call example repeats the unpinned npx -y ...@latest pattern, which is a classic software supply-chain weakness. Because the skill explicitly encourages shell execution, the context increases risk: exploitation would occur on the agent host itself, not merely within generated text.
No suspicious patterns detected.
