Summary Generator
Security checks across malware telemetry and agentic risk
Overview
This is a read-only lead summary skill with clear boundaries and no executable or persistence behavior in the artifacts.
Install only where the agent is allowed to read the intended lead dataset for aggregate summaries. Keep runtime permissions limited to read-only, date-scoped access, and review any downstream chained skills separately before allowing them to suggest or perform actions.
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.