Security audit
Wiki Normalize
Security checks across malware telemetry and agentic risk
Overview
The supplied scan telemetry is clean, but the target skill artifact was not available in the workspace for independent content review.
Install only if the publisher and skill description are familiar to you. Because the actual skill files were not available for this adjudication, review the skill contents and requested permissions in your OpenClaw client before enabling it, especially any access to local files, credentials, network services, or long-running behavior.
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.