SKILLEMALL.ai
GitHub ↗ RU Sign in

BF email-digest

邮件日报专业版面向企业用户与高效能个人用户。Use when 需要消息发送、通知推送、邮件短信、通信集成时使用。不适用于垃圾信息群发。适用于个人开发者、团队协作和自动化流程场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。提供结构化输出和错误处理机制。支持多场景应用和灵活配置。

ClawHub Hermes author: 天轰穿 v1.0.0 MIT-0 2 files body ≈ 2 412 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 35/100 · Will not run — References files that are not bundled: references/style.md, assets/output.json

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
95
Quality 40%
57
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: references/style.md, assets/output.json
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Exfiltration exfil-webhook-url SKILL.md:309
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "webhook": "https://hooks.slack.com/services/详情见说明"
    quoted

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

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Map keys must be unique at line 29, column 1: category: Communication homepage: "https://skillhub.cn/skill/" ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning description-long-hermes description is 154 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning missing-ref reference to a missing file: references/style.md
  • warning missing-ref reference to a missing file: assets/output.json
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "summary_zh"
  • note frontmatter-key unknown frontmatter key "edition"
  • note frontmatter-key unknown frontmatter key "tools"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/style.md, assets/output.json
  • 0Tools and files. 2 referenced file(s) missing: references/style.md, assets/output.json
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 48 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2412 tokens
  • 100Running it twice. No mutating operations
  • low 14 top-level sections: this looks like several domains in one skill

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
  • +2Single-language instructions
  • +3Description length 154: enough signal without eating the budget
  • +4Structure: 46 headings
  • +3Step-by-step instructions: 48 items
  • +4Has examples (13 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.

External checks

ClawHub: suspicious
The skill is an email digest helper, but it asks an agent to use logged-in browser sessions, command execution, scheduling, and external push channels for sensitive email content without enough scoping or consent controls.
LLM: suspicious (high) · 10 Aug 2026