clawvault
Security checks across malware telemetry and agentic risk
Overview
This is a coherent memory tool, but it needs review because it installs external code and enables persistent hooks that can access agent transcripts while the promised hook files are not in the reviewed artifact.
Install only if you are comfortable with a persistent memory tool that can read or modify OpenClaw transcripts and run lifecycle hooks after you enable them. Inspect the installed npm package and hook handler locally before enabling hooks, pin package versions where possible, set an explicit CLAWVAULT_PATH, avoid storing secrets in memories, and only use compression on transcripts you are willing to send to the configured LLM provider.
SkillSpector
- 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.