Agent Docs
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill whose security examples are clearly presented as defensive guidance, not operational instructions.
Safe to install as a documentation aid. Review any generated AGENTS.md, SKILL.md, llms.txt, or README content before committing it, and keep security examples clearly labeled so future agents do not treat them as live instructions.
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
64/64 vendors flagged this skill as clean.