Security audit
OpenClaw Security Auditor
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a legitimate OpenClaw security audit helper, but users should review its privacy/data-flow claims before running it on sensitive configs.
Install only if you are comfortable with your OpenClaw configuration being read locally and redacted security findings being analyzed by whatever LLM your OpenClaw instance uses. Use a local model for sensitive deployments, and verify generated reports do not include actual token or API key values.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.