use-maskrun
Security checks across malware telemetry and agentic risk
Overview
This skill is a narrow safety helper that tells agents to run secret-prone commands through an output-masking wrapper, with its limits clearly stated.
Install maskrun only from a source you trust and configure its masking rules for the secret variable names you actually use. Remember that it masks terminal output only; it does not stop the wrapped command from reading credentials, writing files, or using the network.
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
65/65 vendors flagged this skill as clean.