lark-slides
飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 lark-doc）、云文档里的独立画板对象（走 lark-whiteboard）、上传或下载普通文件（走 lark-drive）。
68
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill repeatedly instructs using user-provided tokens (URL path tokens, wiki/node tokens, file_tokens, --presentation values) verbatim in CLI/API commands (e.g., --node-token, --presentation, file_token), which would require the LLM to include sensitive tokens directly in generated output and thus risks secret exfiltration.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The 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.
Why it was flagged
skill 的运行流程会在“读取或分析已有 PPT/读-改-写闭环”中通过 `slides +xml-get` / `xml_presentation.slide.get` 把飞书 Slides（由用户提供的 `/slides/` URL 或 `/wiki/` URL token 指定）里的完整 XML/单页 XML 作为可读文本喂给 LLM；攻击者只要能让流程读取其提交的该 Slides 内容即可触发间接提示注入。
- Repository
- larksuite/cli
- Commit
6646386
- Audited
- Security analysis
Is this your skill?
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.