dingtalk-chat
钉钉群聊与消息。Use when 用户提到 发消息/编辑或撤回消息/单聊/群聊/建群/普通群升级外部群/群昵称/会话分组/群成员管理/@消息/搜索聊天记录/话题回复/收藏消息/机器人群发/Webhook通知/发送或下载消息图片与文件。不做紧急 DING/短信/电话（走 dingtalk-misc）、邮件（走 dingtalk-mail）、班级群（走 dingtalk-misc）。命令前缀：dws chat。
70
88%
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 explicitly instructs embedding credentials as command-line arguments (e.g., `--webhook-token <token>` and `--robot-code <code>`), which requires the LLM to include secret values verbatim in generated commands/outputs.
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
在要求的运行流程中，钉钉消息查询/导出工作流会调用 `dws chat message list`/`list-focused`/`list-topic-replies` 将群聊或单聊消息正文等返回数据直接喂给后续 LLM 响应（如 SOP-7 拉取消息、并可由 lite recipe/脚本导出全部消息），而这些消息内容属于组织内他人/外部作者的自由文本，因此存在被注入的间接 prompt 注入风险。
- Repository
- DingTalk-Real-AI/dingtalk-workspace-cli
- Commit
1877870
- 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.