Bot Police
Security checks across malware telemetry and agentic risk
Overview
This skill is a local bot-risk scoring helper with disclosed containment recommendations and no evidence of hidden data access, persistence, or destructive code.
This is reasonable to install as a bot-behavior scoring and incident-triage aid. If an agent using it is allowed to quarantine bots, restrict permissions, inspect logs, or notify owners, keep those powers explicitly scoped and consider requiring human approval for block or quarantine 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
VirusTotal findings are pending for this skill version.