ClawHub
Back to skill

Security audit

Remote Jobs Finder

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed remote-job-search skill that uses a server-side Remote Rocketship API key and remembered job preferences; I found no hidden, destructive, or unrelated behavior.

Install this only if you want a Remote Rocketship-powered OpenClaw job-search assistant. Review the gateway extension before installing, back up any existing ~/.openclaw/extensions files, keep RR_API_KEY server-side, and avoid sharing more job-search preference detail than needed if the agent stores preferences or scheduled checks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrases are broad enough to match ordinary conversation, which can cause the skill to activate unexpectedly and invoke the rr_jobs_search tool without sufficiently clear user intent. In a chat environment like WhatsApp, ambiguous activation increases the chance of unintended external queries, privacy leakage of user preferences, and confusing autonomous behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal