SKILLEMALL.ai
GitHub ↗ RU Sign in

CF dingtalk-auto-reply

监控钉钉未读会话，单聊用 AI 以本人身份自动回复（普通员工口吻、平级回同事），群聊/指定名单只发微信提醒（不代发，防社死）。覆盖 dws 未读接口、CodeBuddy Agent SDK 生成回复的 SERVER__PORT 端口冲突坑、自报家门坑、回复自己坑。当用户要求「钉钉自动回复/钉钉代回/监听钉钉未读+AI回复」时使用。

ClawHub Agent Skills author: Azrael Noah v0.1.7 MIT-0 16 files · 1 script body ≈ 10 619 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

监控钉钉未读会话，单聊用 AI 以本人身份自动回复（普通员工口吻、平级回同事），群聊/指定名单只发微信提醒（不代发，防社死）。覆盖 dws 未读接口、CodeBuddy Agent SDK 生成回复的 SERVERPORT…

As a process F 36/100 · Will not run — References files that are not bundled: mediaId=@lQLP..., mediaId=...

IntegrationSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
70/100
safety, quality, tests
Safety 60%
84
Quality 40%
50
Run on models
none yet
Process rating
F
36/100
Will not run
References files that are not bundled: mediaId=@lQLP..., mediaId=...
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 12

✓ No critical or high findings

Medium and low: 12
  • medium Dangerous commands cmd-persistence SKILL.md:416
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    启动器 `.vbs` **不随技能分发**（见上方移植说明，已被 `.gitignore` 排除），由本机 `gen_launcher.py` 生成到 `%APPDATA%\Microsoft\Windows\Start Menu\Programs\Startup\`。两种落地方式，任选其一（或都做）：
    quoted
  • low Exfiltration read-dotenv README.md:108
    Reads a .env file
    # 4) 填私密身份： cp .env.example .env  → 编辑填 BOSS_UID / SELF_OPENDINGTALK_ID 等
  • low Dangerous commands cmd-background-process README.md:122
    Starts a background / autostarted process
    nohup "$PY" dingtalk_unread_monitor.py > ~/.workbuddy/dingtalk_auto_daemon.log 2>&1 & disown
  • low Exfiltration read-dotenv README.md:137
    Reads a .env file (quoted — discussed, not commanded)
    技能目录自带 `.env.example`，`cp .env.example .env` 后按需填写。所有项均可选，留空 = 自动探测 / 默认。常用：
    quoted
  • low Exfiltration read-dotenv README.md:188
    Reads a .env file (quoted — discussed, not commanded)
    - **`.env` 不分发**：已被 `.gitignore` 忽略，切勿提交或外发。换机 `cp .env.example .env` 自行填写。
    quoted
  • low Exfiltration read-dotenv README.md:203
    Reads a .env file (documentation table row)
    | 私密 `.env` | ⚠️ 不随分发，`cp .env.example .env` 后填 |
    table
  • low Exfiltration read-dotenv SKILL.md:19
    Reads a .env file (code comment)
    ├── .env.example                  # 配置样例（cp .env.example .env 后填写真实身份/Key）
    comment
  • low Exfiltration read-dotenv SKILL.md:84
    Reads a .env file (quoted — discussed, not commanded)
    4. **填私密身份**：`cp .env.example .env`（若还没建）→ 在 `.env` 填 `BOSS_UID` / `SELF_OPENDINGTALK_ID` / `SELF_SENDERS` / `MENTION_NAMES` 等（详见下方「隐私与身份配置」）。
    quoted
  • low Exfiltration read-dotenv SKILL.md:141
    Reads a .env file (quoted — discussed, not commanded)
    - **`.env` 不分发**：已被 `.gitignore` 忽略，切勿提交或随技能打包外发。换机时 `cp .env.example .env` 后自行填写。
    quoted
  • low Exfiltration read-dotenv SKILL.md:229
    Reads a .env file (documentation table row)
    | 私密配置 `.env` | skill 内 `.env.example`（`.env` 已被 `.gitignore` 排除） | ⚠️ 不随分发 | 新机 `cp .env.example .env` 后填 `BOSS_UID`/`SELF_OPENDINGTALK_ID` 等。 |
    table
  • low Exfiltration read-dotenv SKILL.md:245
    Reads a .env file
    cp ~/.workbuddy/skills/dingtalk-auto-reply/.env.example ~/.workbuddy/skills/dingtalk-auto-reply/.env
  • low Dangerous commands cmd-background-process SKILL.md:438
    Starts a background / autostarted process
    > ~/.workbuddy/dingtalk_auto_daemon.log 2>&1 & disown

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 10619 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: mediaId=@lQLP...
  • warning missing-ref reference to a missing file: mediaId=...
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: mediaId=@lQLP..., mediaId=...
  • 0Tools and files. 2 referenced file(s) missing: mediaId=@lQLP..., mediaId=...
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 34 mutating operations with no state check
  • 40Execution cost. Instruction body is 10619 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 160 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 22 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (29 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -244 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 166: enough signal without eating the budget
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 160 items
  • +4Has examples (12 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.

External checks

ClawHub: suspicious
This skill is not clearly malicious, but it needs Review because it can run persistently, auto-send DingTalk messages as the user, and give chat-triggered agents broad local and account access.
LLM: suspicious (high) · 2 Sept 2026