A developer has released mcp-secrets-runner, an open-source tool that prevents live API keys from being committed in MCP configuration files. The tool authenticates with machine credentials from secre…
Infisical has introduced Agent Vault, an HTTP credential proxy designed to secure AI agent tool calls by injecting credentials on the fly and enforcing least-privilege boundaries. The proxy intercepts…
Infisical launched Agent Proxy on July 30th, a credential proxy that lets AI agents call external services without receiving the underlying API keys, preventing credential theft via prompt injection. …
Ironrun, a new open-source tool, seals AI agents' access to secrets like API keys and database URLs by running them in an encrypted workspace with time-boxed leases and redacting secrets from output. …
A developer released Sandbox-proxy, a zero-dependency Go forward proxy that injects credentials into outbound requests on the wire, allowing sandboxed code to use tokens without seeing them. The tool …
Credential brokering is emerging as a security pattern to prevent AI agents from leaking secrets via prompt injection, with companies like Anthropic, Vercel, and Cloudflare implementing proxy-based so…