intimate-ch02-research-methods
Security checks across malware telemetry and agentic risk
Overview
The available evidence does not show hidden, destructive, or purpose-mismatched behavior in this skill.
This appears safe to install based on the available evidence, but because the target artifact was not separately visible in the workspace, review the skill text before use and confirm it matches the actions you expect it to perform.
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
66/66 vendors flagged this skill as clean.