Report Review
Security checks across malware telemetry and agentic risk
Overview
This is a report-review checklist skill with no code, credentials, persistence, or external access requested.
This skill appears safe to install as a structured checklist for reviewing reports before completion. It may make the agent more demanding about evidence and validation, but the artifacts do not request special permissions or sensitive access.
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
63/63 vendors flagged this skill as clean.