获取飞书云文档内容。返回文档的 Markdown 内容,支持处理文档中的图片、文件和画板(需配合 feishu_doc_media 工具)。
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
The canonical home for this skill is feishu-fetch-doc in op7418/CodePilot
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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.
SKILL.md:45-48 and SKILL.md:52-67 describe runtime fetching/parsing of a user-supplied Feishu document/wiki URL (or wiki token) and then downloading associated media, so the LLM context can include externally authored document content (public/outsider-hosted wiki/doc text) after tool execution—an indirect prompt-injection pathway.
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 explicitly accepts and fetches Feishu document URLs at runtime (e.g., https://xxx.feishu.cn/docx/Z1FjxxxxxxxxxxxxxxxxxxxtnAc), returning markdown content that will be injected into the agent context and can directly influence prompts.
dadfb1c
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.