Security audit
Security checks for vulnerabilities and agentic risk
The skill is read-only and purpose-aligned for Tieba research, but it runs an unpinned latest npm package with a SocialDataX API key, so users should review that supply-chain risk before installing.
Use this only if you trust SocialDataX and the current npm package. Prefer a pinned, reviewed package version instead of `@latest`, run it in a constrained environment, and use a revocable API key with no unrelated secrets exposed.
The file is entirely written as a Chinese-only skill description and repeatedly instructs the agent in Chinese, but it does not state that use of Chinese is optional or limited to a region-specific compliance need. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The skill instructs agents to execute npx -y socialdatax-skills@latest ..., which fetches and runs the newest package version at runtime rather than a reviewed, fixed release. If the upstream package is compromised, publishes a breaking/malicious update, or the dependency chain is hijacked, agents will execute untrusted code immediately in the user's environment.
This command also uses npx -y socialdatax-skills@latest, causing runtime execution of whatever code is currently published under that package name. That creates a software supply-chain risk because the skill effectively delegates trust to future package releases that were not reviewed when the skill was authored.
The example invokes an unpinned package via npx, which means execution depends on mutable upstream state. In agent environments that may have access to secrets like SOCIALDATAX_API_KEY, a malicious or compromised release could exfiltrate credentials or run arbitrary code.
Because this command dynamically executes the latest npm package version, the actual code run can change over time without any skill-file change. That undermines reproducibility and creates a realistic path for supply-chain compromise to become arbitrary code execution in the agent context.
This unpinned npx usage exposes users to execution of unreviewed future package contents. Since the skill explicitly expects local node, npm, and an API key in the environment, compromise of the package could impact both system integrity and secret confidentiality.
The skill encourages direct execution of a mutable remote package at runtime. Any malicious update or dependency compromise would be executed with the agent's privileges, making this a substantive supply-chain vulnerability rather than a documentation-only concern.
Using npx -y ...@latest for comment retrieval has the same core issue: trust in an ever-changing upstream package. In practice, this can lead to arbitrary code execution, data exfiltration, or unexpected behavior if the package or one of its dependencies is compromised.
This reply-fetching command executes an unpinned npm package, so the code path is not fixed or auditable over time. That makes the skill materially more dangerous because it is an execution instruction, not merely a link or reference, and it occurs in an environment that likely has network access and credentials.
No suspicious patterns detected.
