SKILLEMALL.ai
GitHub ↗ RU Sign in

BC qb-cli

QuickBooks Online CLI tool. Manage customers, invoices, payments, bills, vendors, accounts, items, expenses, journal entries, deposits, transfers, estimates, purchase orders, and run financial reports directly via the Intuit API. 164 commands across 29 command groups. All commands return JSON by default for agent consumption.

ClawHub Agent Skills author: dukecontractors1 v1.0.0 47 files · 1 script body ≈ 5 826 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, progress reporting

IntegrationDockerFinancetype 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
B
79/100
safety, quality, tests
Safety 60%
92
Quality 40%
59
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: qb-cli (ClawHub)

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. 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.
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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Exfiltration exfil-webhook-url src/qb/auth/oauth.py:15
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    REDIRECT_URI = f"https://officially-nonfatalistic-baylee.ngrok-free.dev/callback"
    quoted
  • low Exfiltration read-dotenv README.md:19
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv SKILL.md:28
    Reads a .env file (quoted — discussed, not commanded)
    - run: "cp ~/skills/qb-cli/.env.example ~/skills/qb-cli/.env"
    quoted
  • low Exfiltration read-dotenv SKILL.md:50
    Reads a .env file
    cp ~/skills/qb-cli/.env.example ~/skills/qb-cli/.env

Files scanned: 47. 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 ≈ 5826 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "install"

Process rating: all ten parameters 59/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Failures and branches. 4 branches
  • 70Execution cost. Instruction body is 5826 tokens
  • 100Steps. 56 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 327: enough signal without eating the budget
  • +4Structure: 51 headings
  • +3Step-by-step instructions: 56 items
  • +4Has examples (39 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
This appears to be a real QuickBooks CLI, but its login flow uses an undocumented external ngrok callback and it can change financial records with limited safeguards.
LLM: suspicious (high) · VirusTotal: malicious · 27 May 2026