TensorFlow
Security checks across malware telemetry and agentic risk
Overview
This is a TensorFlow troubleshooting reference skill that does not ask the agent to run commands, access private data, or change the system.
This appears safe to install as a TensorFlow reference. Treat its advice as normal technical guidance, and review GPU memory or training configuration changes before applying them to important workloads.
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.