ClawGuardrails
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only safety skill that routes risky commands, messages, and external actions through guarded approval-aware tools.
This appears safe to install as a guardrail skill. Its usefulness depends on the host environment actually providing and enforcing safe_exec, safe_send, and safe_action; by itself, it does not add code, persistence, credentials, or hidden 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
66/66 vendors flagged this skill as clean.