Security audit

Anthropic Vertex

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent OpenClaw model provider plugin that uses Google Vertex AI credentials to enable Claude models, with no hidden persistence or unrelated behavior found.

Install this only if you intend OpenClaw to use your Google Cloud ADC credentials for Anthropic Vertex model calls. Check that your configured project, region, and any custom base URL are correct because usage may incur Google Cloud costs and uses credentials with Vertex access.

SkillSpector

SkillSpector was not run because this plugin release contains no bundled skills.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/stream-runtime.js:41
Evidence: function createAnthropicVertexStreamFn(projectId, region, baseURL, deps = defaultAnthropicVertexStreamDeps, env = process.env) {