SKILLEMALL.ai
GitHub ↗ RU Sign in

BC openclaw-rpa

Record browser, Excel, Word & API actions once — replay without the LLM: faster, cheaper, no hallucinations. github.com/laziobird/openclaw-rpa . Supports computer-use automation: web clicks/fill/extract, local Excel (.xlsx via openpyxl), Word (.docx via python-docx), HTTP API calls (httpx GET/POST), and auto-login cookie reuse. · Triggers: #rpa #RPA #rpa-api #rpa-login #rpa-login-done #rpa-autologin #rpa-autologin-list #rpa-list #rpa-run #rpa-help · Use when user says RPA, 录制自动化, browser automation, or asks to automate browser/file tasks.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: laziobird v1.3.1 MIT-0 35 files · 1 script body ≈ 2 209 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions

IntegrationGitHubWordExcelPlaywrightData and analyticsSoftware developmentInfrastructuretype 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
77/100
safety, quality, tests
Safety 60%
71
Quality 40%
85
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
When it triggers w 12
50
Failures and branches w 10
55
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.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

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. 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.
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

  • high Concealment en-hide-from-user SKILL.en-US.md:319
    Instruction to hide actions from the user
    - **Exit 0** → **Output nothing to the user.** Silently run `record-start` (below) with `--profile`, then output **only** the verbatim RECORDING template. Do NOT say "Dependencies checked", "browser i
Medium and low: 3
  • medium Exfiltration intent-browser-credential-store articles/autologin-tutorial.en-US.md:197
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    A: Default path: `~/.openclaw/rpa/sessions/<domain>/cookies.json`. If you already have a Playwright-compatible cookie JSON (exported from Chrome DevTools, EditThisCookie, etc.), just drop it at that p
    quoted
  • medium Exfiltration intent-browser-credential-store articles/autologin-tutorial.md:267
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    A：默认路径 `~/.openclaw/rpa/sessions/<域名>/cookies.json`。如果你已有从 Chrome DevTools 或其他工具导出的 Playwright 兼容格式 Cookie JSON，可以直接放到对应路径，无需执行 `#rpa-login`。
    quoted
  • low Secrets in code secret-password-literal README.zh-CN.md:181
    Hard-coded password / key literal (may be an example)
    示例: https://www.alphavantage.co/query?function=…&symbol=IBM&apikey=…

Files scanned: 35. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 63/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 50When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 85Steps. 16 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2209 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 12 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)
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 544: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 16 items
  • +3Output format is stated explicitly
  • +4Has examples (2 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: suspicious
This is a real RPA automation skill, but it stores and reuses sensitive credentials and runs generated Python with broad local authority.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026