Nm Tome Research
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed research workflow that can call helper agents and save research output files, with no hidden install-time code or malicious behavior found.
Install this only if you want an agent-driven research workflow. Expect it to dispatch referenced research agents and create local research/session files in the workspace; avoid sensitive topics unless you trust the external Tome agents or full Claude Code plugin components they rely on.
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.