SKILLEMALL.ai
GitHub ↗ RU Sign in

DD max-banking

>

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Jonatan Costa v1.0.0 MIT-0 7 files · 2 scripts body ≈ 5 354 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype 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
46/100
safety, quality, tests
Safety 60%
52
Quality 40%
36
Run on models
none yet
Process rating
D
42/100
Unfinished process
Result and completion w 14
0
When it triggers w 12
0
Inputs and preconditions w 11
0
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.

Exfiltration
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. 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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 7

  • high Exfiltration exfil-webhook-url README.md:58
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    bash ~/.openclaw/skills/max-banking/scripts/maxbank.sh setup ABCD-EF12 local https://xxx.ngrok-free.app/mcp
Medium and low: 6
  • medium Exfiltration exfil-webhook-url README.md:13
    Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row)
    | **local** | Dev com ngrok | `https://seu-ngrok.ngrok-free.app/mcp` |
    table
  • medium Exfiltration exfil-webhook-url scripts/connect-mcp.js:5
    Webhook / callback URL commonly used for exfiltration (verify the destination) (code comment)
    *   MCP_URL: ex. https://xxx.ngrok-free.app/mcp
    comment
  • medium Exfiltration exfil-webhook-url scripts/connect-mcp.js:32
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    fail('pairing_code obrigatório. Uso: node connect-mcp.js ABCD-EF12 https://xxx.ngrok-free.app/mcp');
    quoted
  • medium Exfiltration exfil-webhook-url scripts/connect-mcp.js:35
    Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition)
    fail('MCP_URL obrigatório (2º argumento). Ex: node connect-mcp.js ABCD-EF12 https://xxx.ngrok-free.app/mcp');
    detector
  • medium Exfiltration exfil-webhook-url SKILL.md:289
    Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row)
    | **URL_MCP** | URL completa (começa com `http://` ou `https://`) | `https://xxx.ngrok-free.app/mcp` |
    table
  • medium Exfiltration exfil-webhook-url SKILL.md:300
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    - Ambiente `local` sem URL → "Qual a URL do MCP? (ex: [https://xxx.ngrok-free.app/mcp](https://xxx.ngrok-free.app/mcp))"
    quoted

Files scanned: 7. 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: Invalid escape sequence \. at line 59, column 15: - pattern: "\.(jpg|jpeg|png|webp)" ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning description-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5354 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "permissions"
  • note frontmatter-key unknown frontmatter key "triggers"

Process rating: all ten parameters 42/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 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
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5354 tokens
  • 100Steps. 95 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. No mutating operations
  • low 13 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)
  • +3Description length 1: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 95 items
  • +4Has examples (9 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 36.

External checks

ClawHub: suspicious
This banking skill has a real purpose, but it can create PIX and boleto payment requests from broad or ambiguous inputs and stores banking credentials locally, so it needs Review before use.
LLM: suspicious (high) · VirusTotal: malicious · 28 May 2026