SKILLEMALL.ai
GitHub ↗ RU Sign in

DF Binance Enhanced Skill

1. Complete test infrastructure — mock files, integration tests, connection verification 2. Security — rate limiting system, API key encryption, detailed logging 3. UX/UI — natural language command...

Not recommendedlow grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 80 files · 8 scripts body ≈ 2 552 tokens Open the sourcegithub.com↗ analyzed 3 d ago

1. Complete test infrastructure — mock files, integration tests, connection verification 2. Security — rate limiting system, API key encryption, detailed…

As a process F 30/100 · Will not run — References files that are not bundled: README_EN.md, LICENSE

IntegrationTelegramDockerKubernetesGitHubInfrastructuretype 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
D
48/100
safety, quality, tests
Safety 60%
44
Quality 40%
54
Run on models
none yet
Process rating
F
30/100
Will not run
References files that are not bundled: README_EN.md, LICENSE
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.

Obfuscation 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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

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 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 · 28

✓ No critical or high findings

Medium and low: 28
  • medium Exfiltration exfil-webhook-url monitoring/telegram.py:17
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    self.base = f'https://api.telegram.org/bot{self.token}' if self.token else None
    quoted
  • medium Exfiltration net-credential-use setup-github-integration.sh:15
    Credential used in a network call (verify the destination is the intended service)
    if ! curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • medium Exfiltration net-credential-use setup-github-integration.sh:25
    Credential used in a network call (verify the destination is the intended service)
    if curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • medium Obfuscation uni-mixed-script-word telegram-bot/bot.py:67
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    send_message(chat_id, 'Ордeр подтверждён. (Прототип — не отправляет на биржу)')
  • medium Obfuscation uni-mixed-script-word telegram-bot/utils.py:33
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    lines.append(f"{emoji} <b>Ордeр</b>")
  • medium Obfuscation uni-mixed-script-word ux/telegram_bot_prototype.py:42
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    return {'chat_id': chat_id, 'text': 'Ордeр отправлен (прототип).'}
  • medium Obfuscation uni-mixed-script-word ux/templates.py:25
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    lines = [f"Ордeр для подтверждения:", f"{side} {qty} {sym} ({otype})"]
  • low Exfiltration read-dotenv DOCUMENTATION.md:29
    Reads a .env file (documentation of a security skill)
    cp templates/.env.example .env
    security skill
  • low Exfiltration read-dotenv DOCUMENTATION.md:46
    Reads a .env file (documentation of a security skill)
    cp templates/.env.example .env
    security skill
  • low Dangerous commands cmd-privilege GITHUB_INTEGRATION.md:204
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo chown -R $USER:$USER ~/.openclaw/skills
    security skill
  • low Secrets in code secret-github-token GITHUB_TOKEN_GUIDE.md:5
    GitHub token (placeholder value)
    Токен `ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx` был отправлен в открытом виде в чат.
    placeholder
  • low Secrets in code secret-github-token GITHUB_TOKEN_GUIDE.md:13
    GitHub token (placeholder value)
    -H "Authorization: token ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
    placeholder
  • low Secrets in code secret-github-token GITHUB_TOKEN_GUIDE.md:15
    GitHub token (placeholder value)
    -d '{"access_token":"ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}'
    placeholder
  • low Secrets in code secret-github-token GITHUB_TOKEN_GUIDE.md:20
    GitHub token (placeholder value)
    - Найдите токен `ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx`
    placeholder
  • low Secrets in code secret-github-token GITHUB_TOKEN_GUIDE.md:33
    GitHub token (placeholder value)
    ./setup-github-secure.sh ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx S7cret
    placeholder
  • low Exfiltration read-dotenv GITHUB_TOKEN_GUIDE.md:73
    Reads a .env file (documentation of a security skill)
    source .env
    security skill
  • low Exfiltration read-dotenv openclaw-config.json:166
    Reads a .env file (quoted — discussed, not commanded)
    "Copy templates/.env.example to .env and configure",
    quoted
  • low Exfiltration read-dotenv README_RU.md:38
    Reads a .env file (documentation of a security skill)
    cp templates/.env.example .env
    security skill
  • low Dangerous commands cmd-privilege README_RU.md:252
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo cp systemd/binance-enhanced.service /etc/systemd/system/
    security skill
  • low Dangerous commands cmd-background-process README_RU.md:254
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable binance-enhanced
    security skill
  • low Exfiltration read-dotenv README.md:40
    Reads a .env file (documentation of a security skill)
    cp templates/.env.example .env
    security skill
  • low Secrets in code secret-github-token setup-github-integration.sh:9
    GitHub token (placeholder value)
    GITHUB_TOKEN="ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
    placeholder
  • low Secrets in code secret-github-token setup-github-secure.sh:15
    GitHub token (placeholder value)
    echo "Please run: ./setup-github-secure.sh ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx S7cret"
    placeholder
  • low Exfiltration net-credential-use setup-github-secure.sh:30
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    USER_INFO=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
    security skill
  • low Exfiltration read-dotenv SKILL_RU.md:114
    Reads a .env file (documentation of a security skill)
    cp templates/.env.example .env
    security skill
  • low Exfiltration read-dotenv SKILL.md:101
    Reads a .env file (documentation of a security skill)
    cp templates/.env.example .env
    security skill
  • low Exfiltration exfil-webhook-url telegram-bot/bot.py:88
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    r = requests.get(f'https://api.telegram.org/bot{BOT_TOKEN}/setWebhook', params={'url': webhook_url})
    placeholder
  • low Exfiltration exfil-webhook-url telegram-bot/bot.py:155
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    r = requests.post(f'https://api.telegram.org/bot{BOT_TOKEN}/sendMessage', data=payload)
    placeholder

Files scanned: 74. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: README_EN.md
  • warning missing-ref reference to a missing file: LICENSE

Process rating: all ten parameters 30/100

Will not run. References files that are not bundled: README_EN.md, LICENSE
  • 0Tools and files. 2 referenced file(s) missing: README_EN.md, LICENSE
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 5 mutating operations with no state check
  • 40Consistency. Frontmatter name (Binance Enhanced Skill) differs from the folder (binance-enhanced)
  • 100Steps. 86 steps
  • 100Execution cost. Instruction body is 2552 tokens
  • 100Progress reporting. Reports progress
  • low 15 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
  • -2localhost URLs: will not work for another user
  • -219 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 200: enough signal without eating the budget
  • +4Structure: 46 headings
  • +3Step-by-step instructions: 86 items
  • +4Has examples (11 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.