DeepInspect Guardrails
Security checks across malware telemetry and agentic risk
Overview
This skill is a local command-risk classifier that reads its bundled policy and reports allow, approval, or block decisions without executing commands or accessing external data.
Safe to install as a local advisory guardrail. Before relying on it for enforcement, tune policy.baseline.json for your workspace and remember that an allow result only means the command did not match the bundled risk patterns.
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.