Open Sentinel - Agent Reliability Layer
Security checks across malware telemetry and agentic risk
Overview
This appears to be a legitimate defensive LLM proxy, but its main description overstates blocking protection compared with its documented async, fail-open behavior.
Review before installing if you plan to rely on this as a hard safety boundary. Test whether your chosen engine and mode actually block unsafe outputs before users or downstream tools see them, scope provider API keys carefully, review the upstream PyPI package, and disable or tightly control tracing for sensitive traffic.
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
48/48 vendors flagged this skill as clean.