create-team
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed playbook for generating Claude Code agent-team skills, with powerful but purpose-aligned agent, file-editing, and optional hook behavior under user control.
Before using a generated team, review every generated agents/<role>.md file, keep tool allowlists narrow, prefer project-scoped .claude/agents over user-wide installation, inspect any hook scripts before enabling them, and run the teardown steps when the team is finished.
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.