Agent Lens
Security checks across malware telemetry and agentic risk
Overview
This skill is a local API-cost tracking guide with disclosed storage and no evidence of hidden or harmful behavior.
Reasonable to install if you want local LLM cost observability. Be aware it records API usage metadata in a local database and installs code from a GitHub repo, so review the upstream package if you will use it with sensitive workloads.
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.