小红书内容发布技能。支持两种发布模式:(1) 上传图文模式 - 图片+短文;(2) 写长文模式 - 长篇文章+排版模板。 支持两种输入方式:用户提供完整内容和图片/图片URL,直接发布;或提供网页URL,自动提取内容和图片。 用户说"发长文"时使用长文模式,否则默认图文模式。
78%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/post-to-xhs/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
SKILL.md 的“网页 URL → WebFetch 提取内容和图片”流程会在运行时把用户提供的网页内容(外部网页文本/可能的注入内容)读入并用于后续摘要与发布,从而可能进入代理的 LLM 上下文;但该工作流文本本身未展示 WebFetch 的具体实现细节。
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill navigates to and scrapes the Xiaohongshu creator page at https://creator.xiaohongshu.com/publish/publish at runtime and uses the extracted template names to populate user prompt options (TEMPLATES), so this external URL directly controls prompts during execution.
xpzouying/xiaohongshu-mcp
bb6fa2e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.