SRE & Incident Management Platform

Security checks across malware telemetry and agentic risk

Overview

This appears to be a documentation-only SRE skill whose operational examples are relevant to incident response, but users should treat remediation examples as potentially disruptive.

Installers should read the remediation sections carefully before using them in production. Treat pod deletion, log cleanup, connection termination, and certificate renewal as manual, reviewed actions unless your environment has its own approved runbooks and safeguards.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill includes auto-remediation patterns that perform state-changing operations such as deleting pods, cleaning logs/archive data, killing connections, and triggering certificate renewal. In an agent skill context, documenting these actions without explicit confirmation gates, safety constraints, and warnings can normalize or enable destructive automation that may be executed in production, causing service disruption, forensic data loss, or unintended configuration changes.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal