Security audit
Rotifer Self-Evolving Agent
Security checks across malware telemetry and agentic risk
Overview
This skill is a clearly disclosed developer tool for comparing and user-approved upgrading of local Rotifer agent capabilities, with high-impact permissions that match its purpose.
Review this before installing if you are uncomfortable with a skill that can fetch a pinned npm MCP server, download third-party Genes, write into the current project, and execute local Agents. Use it only in projects where changing Genes is intended, check proposed upgrades before approving them, and set ROTIFER_TELEMETRY=0 if you do not want Rotifer usage reporting or install-count calls.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.