xiaohongshu ｜小红书 AI 宣传图和图文笔记技能

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This skill does what it says, but it asks for a live Xiaohongshu session cookie and can store or reuse it from local memory without strong safety warnings.

Review before installing. Use this only if you are comfortable giving the skill a live Xiaohongshu session cookie and sending draft descriptions/prompts to OpenAI. Prefer an environment variable or a secret manager over plaintext memory files, remove or rotate the cookie after use, and only run the publishing script when you intentionally want public account content posted.

SkillSpector (4)

By NVIDIA

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill instructs users to supply and optionally store a full Xiaohongshu account cookie in an environment variable or local memory file, but it does not provide a strong security warning about the sensitivity of this credential or the risks of local persistence. If exposed, the cookie could enable account takeover, unauthorized posting, and access to session-scoped account data.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The script sends the user-provided description directly to a remote OpenAI API, but gives no explicit notice that the text will leave the local machine. If users include sensitive business, personal, or unpublished marketing information, this can cause unintended data disclosure to a third-party service.

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The image generation path sends composed promotional text, including user-derived content and generated copy, to a remote image API without warning the user about external transmission. This can leak confidential campaign details, internal product names, or sensitive text embedded into prompts.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The script reads a live authentication cookie from environment variables or local memory files without a clear user-facing warning about the sensitivity of that credential or the risks of storing it in plaintext. In an agent/workspace setting, this can lead to accidental credential exposure, reuse of stale high-privilege session tokens, or unintended publication actions if other components can access the same memory paths.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal