Security audit
Swmm Network
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a disclosed SWMM drainage-network data-processing helper that reads user-selected GIS/model files and writes derived model outputs.
This appears safe to install as a modeling/data-processing skill. Review the external Agentic SWMM project before installing its separate toolchain or MCP servers, and expect this skill to read municipal drainage/GIS files you point it at and create derived model files at the output paths you provide.
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.
Static analysis
No suspicious patterns detected.