Security audit
Deep Research for OpenClaw
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed OpenClaw deep-research setup skill whose main risk is that it asks users to clone and run code from an external GitHub repository.
Before installing, review or pin the referenced GitHub repository, inspect the copied prompt files and Python scripts, avoid elevated privileges, and use a limited Tavily key if enabling Tavily-backed scouting. Do not put secrets or sensitive private material into research prompts unless you are comfortable with the configured sub-agent and external search providers handling that data.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.