钉钉群聊与消息。Use when 收发/搜索消息、建群、群治理、Bot/Webhook、文件、AI/A2UI 卡片流式,或仅限 IM 的消息谓词筛选。跨源主题/行为轨迹走 dingtalk-aisearch;DING/班级群走 dingtalk-misc;邮件走 dingtalk-mail。
90%
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
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.
The required chat read paths (`+chat-messages`, `+search-msg`, `+at-me`, `+unread-chats`, and `message list-all`) return message bodies authored by any group or DM participant, including external-group members, so an outsider can post content that the workflow ingests without the agent first selecting that item.
DingTalk-Real-AI/dingtalk-workspace-cli
38d49e4
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.