Logging Observability
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a normal observability guidance skill with no evidence of hidden code, data exfiltration, or unsafe authority.
Before installing, confirm that any examples are adapted to your environment with secret redaction enabled and that telemetry endpoints, retention, and access controls match your privacy and compliance requirements.
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.