Agent Life
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed cloud backup and restore skill for OpenClaw agent state, with sensitive data handling that fits that purpose.
Install only if you trust agent-life.ai and the alf binary with cloud backup of your agent memory and encrypted vault metadata. Use alf export --dry-run before syncing, review .alfignore exclusions, avoid ALF_ALLOW_UNVERIFIED unless you deliberately accept the supply-chain risk, and preview restores before writing into a live workspace.
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
63/63 vendors flagged this skill as clean.
