Observability Slos
Security checks across malware telemetry and agentic risk
Overview
This is a planning guide for observability SLOs and does not ask the agent to run code or access private data.
Safe to install as an advisory reliability-planning workflow. Users should still review any SLOs, alert rules, or error-budget policies an agent drafts before applying them to production operations.
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
62/62 vendors flagged this skill as clean.