Security audit
Runtime Monitor
Security checks across malware telemetry and agentic risk
Overview
This skill is a local security monitor that checks agent inputs and outputs for risky patterns, and its behavior matches its stated purpose.
Install only if you are comfortable with a local monitor inspecting prompts, tool inputs, and tool outputs. Treat generated reports as sensitive because they can include excerpts of the inspected text, and test the block threshold before relying on it in important workflows.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.