CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dingtalk-event

企业自建应用三方事件发送(dws event send),以及钉钉个人 IM、OA 审批、VoIP 通话邀请、待办、日历、互动卡片、好友与听记事件长连接监听。Use when 用户说监听消息/@我/某人/某群/全部消息、已读/撤回/reaction、群成员加入/群成员退出,监听审批任务创建/完成/转交、审批实例发起/抄送/终止/完成、VoIP 通话邀请、待办创建/更新/删除、日程创建/新增参与/修改/取消、好友申请/好友添加成功、听记创建/纪要生成,或互动卡片回调,以及应用事件发现、和事件Schema 查询、实时消费。命令前缀:dws event。

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security
Critical

E004: Prompt injection detected in skill instructions.

What this means

Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.

Why it was flagged

The skill is a DingTalk event-listening and event-sending reference with no sign of malicious intent toward the user; its only risky element is a documented emergency step that clears the local subscription-retry protection records, which weakens a safeguard beyond what a normal listen task needs.

Report incorrect finding
Medium

W013: Attempt to modify system services in skill instructions.

What this means

The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.

Why it was flagged

The skill is a DingTalk event-listening CLI guide with no sudo, system-file, SSH, service, or user-account changes, but it does tell the agent to delete a local subscription-protection state file as an emergency recovery step, which could be read as circumventing a local safeguard.

Low

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

The required `dws event +listen-im` workflow (at-me, sender, group, all-direct, all-group) streams inbound DingTalk messages whose `content` and `sender` fields an outsider can author by messaging the user or posting in a monitored group, without the agent first selecting a specific item.

Repository

DingTalk-Real-AI/dingtalk-workspace-cli

Path

skills/multi/dingtalk-event/SKILL.md

Audited
Security analysis
Snyk

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.