Security audit
OpenClaw Secrets Hygiene
Security checks across malware telemetry and agentic risk
Overview
The reviewed skills are coherent developer and maintainer workflows, with sensitive actions disclosed and generally gated by user direction or confirmation.
Review commands before running workflows that moderate users, publish PR proof, post comments, install packages, or use the autoreview helper's full-access mode. Use only with credentials and repositories you intend the skill to operate on.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.