Indices
Security checks across malware telemetry and agentic risk
Overview
The skill set is mostly coherent, but its review helper defaults to unusually broad full-access execution for nested AI review.
Install only if you trust this publisher for ClawHub maintainer work. Before using autoreview, consider setting AUTOREVIEW_YOLO=0 or passing --no-yolo, and be aware that fallback reviewers may receive code diffs. Use moderation and proof publishing only with explicit targets and after reviewing the exact commands.
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.