SKILLEMALL.ai
GitHub ↗ RU Sign in

CB ymailink

Terminal email client for managing emails from the command line. Supports IMAP/SMTP, Outlook (Graph API), Gmail (Google API), and Exchange backends, plus AI-powered email summarization and quick reply. Use this skill ANYTIME the user mentions email from the terminal — whether they say 'ymailink' by name, ask about sending/reading/searching emails via CLI, need help configuring an email account (IMAP, SMTP, Outlook, Gmail, Exchange), want to automate email notifications in shell scripts, or need to compose/reply/forward/move/copy/delete/flag emails. Also trigger when the user brings up email authentication (OAuth2, app passwords, IMAP credentials), mentions RFC 822 message format, wants to manage email folders, download attachments, or troubleshoot email delivery issues. Also trigger when the user wants AI-powered email summaries, one-line digests, or quick reply suggestions — this skill covers the `ymailink ai` commands. This is the go-to skill for anything email-related in the terminal. Before using ymailink commands, verify it is installed (see Installation section in the skill body).

Not recommendedcritical or high security findings
ClawHub Agent Skills author: 2969192546 v1.1.1 MIT-0 5 files body ≈ 2 960 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 74/100 · Nearly there — weak spots: running it twice

IntegrationGmailOutlookInfrastructureSoftware developmenttype 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
74/100
safety, quality, tests
Safety 60%
82
Quality 40%
63
Run on models
none yet
Process rating
B
74/100
Nearly there
Running it twice w 4
30
Tools and files w 18
60
Result and completion w 14
60
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Shorten the description to 1024 characters.
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

  • high Dangerous commands cmd-install-from-url SKILL.md:39
    Installs a package from an untrusted URL / archive
    pip install git+https://gitee.com/w3hsec/ymailink.git

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1103 chars, limit 1024

Process rating: all ten parameters 74/100

  • 30Running it twice. 27 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, write, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 65Failures and branches. 3 branches
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 22 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2960 tokens
  • 100Progress reporting. Reports progress
  • low 13 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (4 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)
  • +3Description length 1103: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 22 items
  • +3Output format is stated explicitly
  • +4Has examples (18 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.

External checks

ClawHub: suspicious
The skill is a legitimate terminal email helper, but it should be reviewed carefully because it can access and change mailboxes, handle credentials, and send selected email content to an external AI service.
LLM: suspicious (high) · VirusTotal: · 28 May 2026