Security audit
glm-calibration
Security checks across malware telemetry and agentic risk
Overview
This skill is a narrow GLM calibration guide with only markdown instructions and no hidden install, persistence, credentials, or network behavior.
Install this if you work with GLM calibration. Before using the sample optimization code, back up glm3.nml, confirm the glm command is the expected local GLM binary, and run it from the correct model directory.
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.