dws-shared
钉钉(DingTalk) MultiSkill 的轻量共享入口。Use when 用户泛称 DWS/钉钉操作但未明确产品、请求跨产品编排、需要 URL 类型预检或产品边界消歧。清晰的单产品操作优先使用对应 dingtalk-* 子 skill；本 skill 只提供全局执行契约和按需 reference 导航，不承载产品命令全集。
77
100%
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.
W008: Secret detected in skill content (API keys, tokens, passwords).
What this means
Detected sensitive credentials directly embedded within the skill content, such as API keys, access tokens, private keys, or service-specific secrets. Secrets should never be hardcoded in plain text within skill instructions.
Why it was flagged
I flagged literal, high-entropy values that are directly present and used in authentication flows in the documentation. - The DWS channel code (18451e165920b301ade00efae99b2c253e1e900b) appears as a quoted assignment and in the table of available channels and is used in the example dws auth login command. It is a long, random-looking token and is demonstrated as required for successful login in the doc, so it functions as an access-affecting credential (not just a human-readable name). - The profile string 'dingd8e1123006514592:04061459256343' is shown inline in the login example and in the mapping table; it's a non-trivial identifier used in login commands and could be sensitive in context. I therefore treat these as real, potentially usable credentials present in the files. I did not ignore them because they are not placeholders or trivial setup passwords and they are used in example commands that demonstrate login behavior.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
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.
Why it was flagged
The skill instructs the agent to call read_url at runtime to fetch arbitrary shared alidocs content (e.g. read_url("https://alidocs.dingtalk.com/i/p/Y7kmbokZp3pgGLq2")), which would inject remote document text into the agent's context and can directly control prompts/responses.
- 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.