SKILLEMALL.ai
GitHub ↗ RU Sign in

DD smb-sales-boost

Find, preview and export growing local businesses (SMB leads) from the SMB Sales Boost database through its REST API - search by keyword, location and buying signals, preview for free, export CSV/JSON/XLSX, re-download past exports, enrich lists of website URLs, manage saved searches, keyword lists, email schedules, credits and the subscription, and set up CRM and webhook integrations (HubSpot, Salesforce, Pipedrive, Zapier, n8n, Make, Pipedream, Clay, any webhook URL) that send lead data, including business contact details, outside SMB Sales Boost automatically. Requires SMB_SALES_BOOST_API_KEY (smbk_...) and python3. Searches, exports and enrichments spend credits; purchases, plan changes, auto top-up and overage billing charge real money; integrations send lead data to third-party systems; so always confirm with the user first. Exported files contain business contact details (PII).

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Tomsonx232 v1.9.5 MIT-0 6 files · 1 script body ≈ 16 122 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Find, preview and export growing local businesses (SMB leads) from the SMB Sales Boost database through its REST API - search by keyword, location and buying…

As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency

ProcedureExcelSalesforceHubSpotZapierSales and CRMData and analyticstype 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
73/100
safety, quality, tests
Safety 60%
82
Quality 40%
60
Run on models
none yet
Process rating
D
47/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Execution cost w 6
10
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 · 1

  • high Exfiltration exfil-send-secrets-to-url REFERENCE.md:355
    Instruction to send secrets/history to an external endpoint (describes API authentication (bearer / header / HTTPS))
    | 5 | `PATCH /integrations/{id}` | Any of `displayName`, `status` (`connected` or `disabled`; `needs_attention` is set only by the system and sending it is a `400 validation_error`, except as a no-op
    API auth

Files scanned: 6. 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 ≈ 16122 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 133): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 47/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 16122 tokens: crowds the task out of the window
  • 30Running it twice. 171 mutating operations with no state check
  • 40Consistency. Frontmatter name (smb-sales-boost) differs from the folder (smb-sales-boost-skill)
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 85Steps. 78 steps, 1 vague phrases
  • 100Failures and branches. 9 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 17 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 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 897: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 78 items
  • +4Has examples (8 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: suspicious
The skill is mostly transparent and purpose-aligned, but it can make keyword changes that affect active lead email schedules without the bundled script requiring explicit confirmation.
LLM: suspicious (high) · 8 Oct 2026