Transmissions
Security checks across malware telemetry and agentic risk
Overview
This skill is a collection of markdown writings with no executable code; it is safe to install, but users should set boundaries if an autonomous agent follows its file and memory advice.
Installers should understand that this skill is mostly reflective and advisory. If an agent uses it during autonomous work, tell the agent exactly which folders it may read or write, where persistent notes may live, and what actions require approval, especially external posting, emails, destructive commands, or storing sensitive information.
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.