agent-namer
Security checks across malware telemetry and agentic risk
Overview
This is a narrow local helper for generating and tracking internal agent names, with no evidence of hidden network, credential, or broad filesystem behavior.
Install only if you are comfortable with a Python helper maintaining a local name registry in scripts/used_names.json. Review add or kill operations because they change that registry, and avoid putting secrets or sensitive operational details in role descriptions.
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.