SKILLEMALL.ai
GitHub ↗ RU Sign in

BC officex

Complete OfficeX platform skill for end-user consumers and app developers interacting with the OfficeX REST API. Covers the full credit-based app marketplace ("Netflix meets Costco for business apps"). Use when: (1) Making HTTP calls to OfficeX cloud API, (2) Building or publishing apps on the platform, (3) Implementing billing (reserve/settle/sip/payout), (4) Managing users, installs, wallets, (5) Handling webhooks (INSTALL/UNINSTALL/RATE_LIMIT_CHANGE), (6) Embedding apps in iframes, (7) Integrating with the AI chat agent (agent_context, documentation, context_prompt), (8) Debugging API errors or auth issues. Triggers on: officex, cloud officex, credit economy, app marketplace, reserve credits, settle, sip, install app, master key, install secret, wallet, vendor inbox, payout, voucher, OTP, register user, register app, webhook, iframe, agent context, billing pattern.

ClawHub Agent Skills author: OfficeX v1.0.0 2 files body ≈ 10 214 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

IntegrationAI and agentsCommercetype 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
76/100
safety, quality, tests
Safety 60%
80
Quality 40%
71
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

How to improve

  1. 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 net-credential-use SKILL.md:1084
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/purchase-credits -H "x-officex-user-id: $UID" -H "x-officex-master-key: $KEY" \
  • medium Exfiltration net-credential-use SKILL.md:1086
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/install/$APP_ID -H "x-officex-user-id: $UID" -H "x-officex-master-key: $KEY"
  • medium Exfiltration net-credential-use SKILL.md:1093
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/register-app -H "x-officex-user-id: $UID" -H "x-officex-master-key: $KEY" \
  • medium Exfiltration net-credential-use SKILL.md:1108
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/payout -H "x-officex-user-id: $UID" -H "x-officex-master-key: $KEY" \

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 10214 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 22 mutating operations with no state check
  • 40Execution cost. Instruction body is 10214 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 36 steps
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 21 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 880: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 54 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (57 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
OfficeX is a coherent API guide, but it teaches agents and app developers to handle billing/admin credentials and prompt-visible secrets in ways that need careful review.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026