Agent Weave
Security checks across malware telemetry and agentic risk
Overview
Agent Weave appears to be a local master-worker task orchestration skill with expected logging and worker-management behavior, not evidence of theft, hidden execution, or destructive activity.
Before installing, verify the npm package and CLI entry point because the packaged bin metadata appears inconsistent. Use project-local installation where possible, run only trusted task functions, cap worker counts/timeouts for expensive jobs, and treat generated ./agent-logs files as potentially sensitive local data.
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.