AI Agent Observability
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-style observability checklist with no code execution, persistence, credential handling, or hidden behavior.
Installing this skill is reasonable if you treat it as a guide or checklist. Before asking an autonomous agent to run the assessment, give it only explicit read-only access to the monitoring, incident, and billing sources you want reviewed, and avoid granting broad production, credential, or account access unless separately justified.
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.