Reading Squad
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only prompt pattern for simulated book discussions, with no executable code or sensitive access.
Installers should understand this skill produces AI-generated discussion and reading advice, including simulated named perspectives; do not treat outputs as actual statements from those people.
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.