Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent OpenClaw provider plugin that uses Google Vertex AI credentials to make Anthropic model calls, with no evidence of hidden persistence, destructive actions, or unrelated data access.
Install only if you intend OpenClaw to use your Google Cloud ADC credentials for Anthropic Vertex model access. Confirm the selected Google Cloud project and region are correct, because model usage may incur Vertex AI costs under those credentials.
SkillSpector was not run because this plugin release contains no bundled skills.
Detected: suspicious.env_credential_access
function createAnthropicVertexStreamFn(projectId, region, baseURL, deps = defaultAnthropicVertexStreamDeps, env = process.env) {