Security audit
DR Agent Secrets
Security checks across malware telemetry and agentic risk
Overview
This is a text-only procedure for safely configuring local OpenClaw secrets, with clear warnings and no hidden executable code.
Install only if you want a procedural guide for managing persistent local OpenClaw secrets. Review the paths and Daniel-specific naming before use, and make sure any agent following it still asks before changing credential mechanisms, secret locations, permissions policy, or restarting active services.
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.