GLM-Master-Skill
Security checks across malware telemetry and agentic risk
Overview
This is a guide-only GLM skill directory with no executable files, credentials use, or hidden persistence in the reviewed artifact.
Installing this master skill is low risk. Before following its catalog commands, review each downstream GLM skill you choose to install, avoid bulk-installing skills you do not need, and keep any ZHIPU_API_KEY in a secure environment variable or secret store.
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
55/55 vendors flagged this skill as clean.
