agent-search
Security checks across malware telemetry and agentic risk
Overview
This is a very small skill that only declares access to an agent-browser command for listing agents, with no evidence of hidden, persistent, destructive, or data-exfiltrating behavior.
Before installing, confirm that the local agent-browser command is from a source you trust and behaves as a read-only agent listing tool. The submitted skill itself is coherent, but its activation condition and documentation are sparse.
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.