Anthropic Vertex
Security checks across malware telemetry and agentic risk
Overview
This official OpenClaw provider plugin coherently adds Anthropic Claude access through Google Vertex AI and shows no evidence of hidden or malicious behavior.
Install this only if you intend OpenClaw to use your Google Cloud Application Default Credentials for Anthropic Claude calls on Vertex AI. Review which Google project and region your ADC configuration points to, because model requests and billing will go through that account.
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
61/61 vendors flagged this plugin as clean.