Skills/ClawHub/rent-a-person-ai

rent-a-person-ai@1.0.35

CAUTION· static only

Publisher claims: "Hire verified humans for deliveries, errands, meetings, photography, pet care, and other real-world tasks that AI cannot perform." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher saireetikap · publishing for 278 daysInstalls 3,911Last detonated 7 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Tunneling service URL; Tunneling service URL. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
File type combined with upload actionscripts/send-to-session.js:34 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Sending to session: ${sessionKey}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/rentaperson-inject-key-transform.example.js:32 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst env = config?.skills?.entries?.['rent-a-person-ai']?.env || {};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/install-and-setup.sh:20 · npx invocation of non-well-known package — may execute untrusted codenpx clawhub install "$SKILL_NAME" --force --workdir "$WORKDIR"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Tunneling service URLscripts/test-webhook.js:12 · Tunneling service URL — may route traffic to attacker infrastructureconsole.error('Example: node test-webhook.js https://abc123.ngrok.io');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Tunneling service URLSKILL.md:45 · Tunneling service URL — may route traffic to attacker infrastructure- **Webhook URL** (e.g. your ngrok HTTPS URL, e.g. `https://abc123.ngrok.io`)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actionscripts/setup.js:859 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Sending agent brief to main session: ${mainSessionKey}...`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Tunneling service URLscripts/test-webhook.js:83 · Tunneling service URL — may route traffic to attacker infrastructureconsole.error(' https://velia-regardable-reed.ngrok-free.dev');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Tunneling service URLrentaperson-agent.json:6 · Tunneling service URL — may route traffic to attacker infrastructure"webhookUrl": "https://velia-regardable-reed.ngrok-free.dev",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandSKILL.md:29 · File permission modification command — agent changes file ownership/permissionschmod +x openclaw-skill/scripts/install-and-setup.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Tunneling service URLscripts/setup.js:465 · Tunneling service URL — may route traffic to attacker infrastructureconst ngrokUrl = await ask(rl, 'Public webhook URL (e.g. https://abc123.ngrok.io)', '');Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:23 · npx invocation of non-well-known package — may execute untrusted codenpx clawhub install rent-a-person-ai --force --workdir ~/.openclaw/workspace-observer-aligned && node ~/.openclaw/workspace-observer-aligned/skills/rent-a-person-ai/scripts/setup.jsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:119 · npx invocation of non-well-known package — may execute untrusted codenpx ngrok http 3000Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Tunneling service URLscripts/setup.js:448 · Tunneling service URL — may route traffic to attacker infrastructure'Gateway base URL (e.g. https://abc123.ngrok.io)',Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Tunneling service URLscripts/test-webhook.js:5 · Tunneling service URL — may route traffic to attacker infrastructure* Example: node test-webhook.js https://abc123.ngrok.ioFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Tunneling service URLSKILL.md:122 · Tunneling service URL — may route traffic to attacker infrastructureCopy the **HTTPS** URL (e.g. `https://abc123.ngrok.io`), then register:Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actionscripts/setup.js:993 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` curl -X POST http://127.0.0.1:${bridgePort || 3001} \\`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/test-local.js:22 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`📤 Sending to: ${bridgeUrl}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/setup.js:872 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Sending agent brief to webhook session: ${webhookSessionKey}...`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/setup.js:967 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' Send a message or apply to a bounty on RentAPerson');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/test-webhook.js:32 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('📤 Sending test webhook...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/setup.js:956 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' Send a message or apply to a bounty on RentAPerson');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈13,885 tok
1 file · 21 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim saireetikap: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Tunneling service URL≈ +4 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim saireetikapPropose a patch to the maintainer