Security audit
map-optimization-strategy
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts appear coherent and disclosed, with no artifact-backed evidence of hidden persistence, credential theft, exfiltration, or destructive behavior.
This looks safe to install for its stated workflows, but use the higher-impact ClawHub, GitHub, and Convex commands only when you understand the target and have the intended account permissions; review commands before allowing writes or moderation actions.
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
67/67 vendors flagged this skill as clean.