SKILLEMALL.ai
RU Sign in

FB RentAPerson.ai — OpenClaw Agent Skill

1. RentAPerson: Register your agent (POST /api/agents/register) and save your API key — you need it for all API calls. 2. OpenClaw: Enable hooks in your OpenClaw gateway so it can receive HTTP webh...

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 20 files · 2 scripts body ≈ 14 132 tokens Open the sourcegithub.com↗ analyzed 2 d ago

1. RentAPerson: Register your agent (POST /api/agents/register) and save your API key — you need it for all API calls. 2. OpenClaw: Enable hooks in your…

As a process B 72/100 · Nearly there — weak spots: consistency, execution cost

ProcedureWhatsAppAI 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
F
22/100
safety, quality, tests
Safety 60%
0
Quality 40%
55
Run on models
none yet
Process rating
B
72/100
Nearly there
Consistency w 8
40
Execution cost w 6
40
When it triggers w 12
50
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 · 24

  • high Exfiltration exfil-webhook-url bridge/README.md:54
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    # https://abc1….io
  • high Exfiltration exfil-webhook-url scripts/verify-setup.md:39
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    curl -X POST https://velia-regardable-reed.ngrok-free.dev \
  • high Exfiltration exfil-webhook-url scripts/verify-setup.md:52
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    node test-webhook.js https://velia-regardable-reed.ngrok-free.dev
Medium and low: 21
  • medium Exfiltration net-redirectable-api-key bridge/server.js:35
    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
  • medium Exfiltration exfil-webhook-url INSTALLATION.md:152
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "webhookUrl": "https://abc1….io"
    quoted
  • medium Exfiltration exfil-webhook-url INSTALLATION.md:180
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "webhookUrl": "https://abc1….io/hooks/rentaperson"
    quoted
  • medium Exfiltration exfil-webhook-url rentaperson-agent.json:6
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "webhookUrl": "https://velia-regardable-reed.ngrok-free.dev",
    quoted
  • medium Exfiltration net-redirectable-api-key scripts/fetch-test-ids.js:31
    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
  • medium Exfiltration net-credential-use scripts/inject-api-key.js:37
    Credential used in a network call (verify the destination is the intended service)
    const curlArgs = ['-H', `X-API-Key: ${key}`, ...args];
  • medium Exfiltration exfil-webhook-url scripts/verify-setup.md:14
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    - **Forwarding**: `https://velia-regardable-reed.ngrok-free.dev -> http://localhost:XXXX`
    quoted
  • low Dangerous commands cmd-background-process bridge/README.md:104
    Starts a background / autostarted process
    sudo systemctl enable rentaperson-bridge
  • low Exfiltration exfil-webhook-url INSTALLATION.md:142
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    Copy the HTTPS URL (e.g., `https://abc1….io`)
    demoquoted
  • low Dangerous commands cmd-background-process INSTALLATION.md:286
    Starts a background / autostarted process
    sudo systemctl enable rentaperson-bridge
  • low Exfiltration net-credential-use scripts/inject-api-key.js:12
    Credential used in a network call (verify the destination is the intended service) (code comment)
    *   → Runs curl with -H "X-API-Key: $RENTAPERSON_API_KEY" prepended.
    comment
  • low Exfiltration exfil-webhook-url scripts/setup.js:448
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    'Gateway base URL (e.g. https://abc1….io)',
    demoquoted
  • low Exfiltration exfil-webhook-url scripts/setup.js:465
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    const ngrokUrl = await ask(rl, 'Public webhook URL (e.g. https://abc1….io)', '');
    demoquoted
  • low Exfiltration net-credential-use scripts/setup.js:845
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    Example: \`curl -H "X-API-Key: ${apiKey}" "${apiBase}/api/conversations"\`
    quoted
  • low Exfiltration exfil-webhook-url scripts/test-webhook.js:5
    Webhook / callback URL commonly used for exfiltration (verify the destination) (code comment; test fixture / example file)
    * Example: node test-webhook.js https://abc1….io
    commentfixture
  • low Exfiltration exfil-webhook-url scripts/test-webhook.js:12
    Webhook / callback URL commonly used for exfiltration (verify the destination) (test fixture / example file; quoted — discussed, not commanded)
    console.error('Example: node test-webhook.js https://abc1….io');
    fixturequoted
  • low Exfiltration exfil-webhook-url scripts/test-webhook.js:83
    Webhook / callback URL commonly used for exfiltration (verify the destination) (test fixture / example file; quoted — discussed, not commanded)
    console.error('   https://velia-regardable-reed.ngrok-free.dev');
    fixturequoted
  • low Exfiltration exfil-webhook-url scripts/verify-setup.md:65
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - Visit `https://velia-regardable-reed.ngrok-free.dev` in your browser first
    placeholder
  • low Exfiltration exfil-webhook-url SKILL.md:52
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    - **Webhook URL** (e.g. your ngrok HTTPS URL, e.g. `https://abc1….io`)
    demoquoted
  • low Exfiltration exfil-webhook-url SKILL.md:129
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    Copy the **HTTPS** URL (e.g. `https://abc1….io`), then register:
    demoquoted
  • low Exfiltration exfil-webhook-url WEBHOOK_API_KEY_SOLUTION.md:341
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    4. Point RentAPerson webhook at: `https://your-ngrok.ngrok.io` (bridge port)
    placeholder

Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 14132 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 72/100

  • 40Consistency. Frontmatter name (RentAPerson.ai — OpenClaw Agent Skill) differs from the folder (rent-a-person-ai)
  • 40Execution cost. Instruction body is 14132 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 60Steps. 127 steps, 11 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 10 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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)
  • -2localhost URLs: will not work for another user
  • -36 of 10 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 200: enough signal without eating the budget
  • +4Structure: 41 headings
  • +3Step-by-step instructions: 127 items
  • +3Output format is stated explicitly
  • +4Has examples (49 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.