Drawio Studio
Security checks across malware telemetry and agentic risk
Overview
The supplied security telemetry is clean, and I found no artifact-backed evidence of hidden, destructive, or deceptive behavior.
This looks acceptable to install based on the supplied evidence. As with any skill, review what it asks the agent to do before use, and only provide credentials or private data when the skill’s purpose clearly requires it.
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.