famous-en
Security checks across malware telemetry and agentic risk
Overview
This skill is a markdown-only set of human-AI collaboration thought experiments and does not ask the agent to run commands, access data, or make changes.
This appears safe to install as a reference/content skill. Review whether the philosophy and examples fit your intended use, but it does not request access to private data, credentials, tools, or persistent permissions.
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.