SKILLEMALL.ai
GitHub ↗ RU Sign in

BB human-rent

Human-as-a-Service for OpenClaw - Dispatch verified human agents to perform physical world tasks and sensory validation

ClawHub Agent Skills author: Justin Liu v0.1.1 MIT-0 31 files · 2 scripts body ≈ 3 156 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerInfrastructureAI and agentstype 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%
72
Quality 40%
85
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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

    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 · 8

    ✓ No critical or high findings

    Medium and low: 8
    • medium Dangerous commands cmd-shell-rc INSTALLATION.md:91
      Writes to a shell startup file
      echo 'export ZHENRENT_API_KEY="zr_key_your_key_here"' >> ~/.bashrc
    • medium Dangerous commands cmd-shell-rc INSTALLATION.md:92
      Writes to a shell startup file
      echo 'export ZHENRENT_API_SECRET="zr_secret_your_secret_here"' >> ~/.bashrc
    • medium Dangerous commands cmd-shell-rc INSTALLATION.md:96
      Writes to a shell startup file
      echo 'export ZHENRENT_API_KEY="zr_key_your_key_here"' >> ~/.zshrc
    • medium Dangerous commands cmd-shell-rc INSTALLATION.md:97
      Writes to a shell startup file
      echo 'export ZHENRENT_API_SECRET="zr_secret_your_secret_here"' >> ~/.zshrc
    • medium Exfiltration net-redirectable-api-key lib/api-client.js:15
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • low Exfiltration read-dotenv RELEASE-NOTES-v0.2.1.md:283
      Reads a .env file
      cp .env .env.backup
    • low Exfiltration read-dotenv RELEASE-NOTES-v0.2.1.md:292
      Reads a .env file
      cp .env.backup .env
    • low Risky intent intent-offensive-security SECURITY-FIXES-v0.2.1.md:44
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Could be used for lateral movement within infrastructure

    Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 66/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
    • 100Steps. 97 steps
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3156 tokens
    • 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
    • low 19 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
    • +3Description length 119: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +4Structure: 49 headings
    • +3Step-by-step instructions: 97 items
    • +4Has examples (17 code blocks)
    • +1License stated

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

    External checks

    ClawHub: suspicious
    The skill appears purpose-aligned, but it can dispatch paid human workers for real-world tasks and includes an automation bypass that needs careful review.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026