What is AgentSecrets?
The Zero-Knowledge Difference
How AgentSecrets Works
Installation
Quick Start
Migrating from .env Files
Migrating from Vault / AWS
Migrating from dotenv-vault
Production Checklist
Credential Exposure
What Zero-Knowledge Means
The Proxy Model
The Three-Layer Model
Environments
Agent Identity
Storage Modes
The No get() Principle
Secret-Level Policies
Cloud Overview & Architecture
The Dual-Engine Model
Cloud Resolver Data Plane
Workload & Agent Tokens
Egress Allowlists & Audit Streams
Cloud REST API Reference
Account (init / login)
Server & Self-Hosting (server)
Docs
Shell Autocompletion
Keychain Auth
Secrets
Environments
Credential Proxy
env Injection
Workspaces & Teams
Projects
Agent Identity
Audit & Governance
Integrations Overview
Claude Desktop
Cursor
OpenClaw
HTTP Proxy (Any)
LangChain (Soon)
CrewAI (Soon)
CI/CD Pipeline
SDK Overview
Python SDK
Python API Reference
Python SDK Manual Testing
JavaScript SDK (Soon)
Ecosystem Overview
Zero-Knowledge MCP Server
Server Overview
5-Layer Architecture
Self-Hosting Guide
Authentication & Keys
Workspaces & Teams
Projects & Scope
Environments
Secrets & Sync Protocol
Agent Identity Resolution
Telemetry & Metrics Engine
Audit Log Sync
API Endpoint Reference
Security Overview
Anti-Impersonation & Process Verification
Encryption Model
Zero-Knowledge Sync
Proxy Security Layers
Threat Model
OWASP Top 10 Mitigation
Security FAQ
Third-Party Audit
Reporting Vulnerabilities
Guides Overview
Building on the SDK
Stripe Integration
OpenAI Integration
Multi-Agent Setup
Onboarding Team
CI/CD Pipeline
Publishing ZK MCP
Rotating Credentials
Auditing Team Activity
Dev to Production
Kubernetes Deployment
Monorepo Setup
Production Proxy Hardening
vs .env Files
vs HashiCorp Vault
vs AWS Secrets Manager
vs dotenv-vault
vs Infisical
When Not to Use
Proxy Not Starting
Proxy Not Resolving
Domain Blocked
Sync Conflicts
MCP Not Connecting
Session Token Errors
Proxy Session Authorization
Keychain Storage & Backends
SSRF & Destination Rules
Installation Issues
Error Codes Reference
Frequently Asked Questions
v3.1.x
v3.0.0
v2.1.0
v2.0.0
v1.4.0
v1.3.x
v1.2.0
v1.1.x
v1.0.x
Comparisonsvs AWS Secrets Manager

AgentSecrets vs AWS Secrets Manager

AWS Secrets Manager is a robust cloud service for storing and retrieving secrets, deeply integrated into the AWS ecosystem (IAM, KMS, Lambda, ECS, EKS).

Recent Evolution

AWS has made two notable additions since 2025:

Workload Credentials Provider (v3.0.0, June 2026): Rebranded from the Secrets Manager Agent. A local HTTP caching sidecar on localhost:2773 that caches secrets in memory with configurable TTL. Also now handles ACM certificate export/refresh. Open source (Rust).

AI Agent Secret Safety Skill (June 17, 2026): Part of the AWS Agent Toolkit. Two layers — (1) guides agents to use {{resolve:secretsmanager:...}} dynamic references with asm-exec, a wrapper that resolves secrets in a child process; (2) a PreToolUse hook that blocks agents from calling GetSecretValue directly.

What These Don't Change

The Workload Credentials Provider is a caching layer, not a credential broker. It holds the decrypted secret in its own memory cache, and any process with the SSRF token can retrieve it. The secret still reaches the application process in plaintext.

The AI Agent Safety Skill is an agent-level guardrail — it tells the agent not to read secrets, but does not prevent a compromised or misconfigured agent from bypassing it. It depends on the agent respecting the PreToolUse hook, and does not enforce the restriction at the infrastructure level.

Underneath both, GetSecretValue still returns the decrypted SecretString or SecretBinary in the API response. The credential delivery model is unchanged: request-and-receive.

The Core Architectural Difference

AWS Secrets ManagerAgentSecrets
Delivery modelRequest-and-receive — agent calls GetSecretValue, gets plaintextTransport-layer injection — agent passes key name, proxy resolves and injects
Agent sees credentialYes, in API responseNo — credential never enters agent context
Local cachingIn-memory cache (Workload Credentials Provider)OS keychain (persistent, encrypted at rest)
Per-secret constraintsIAM policies (coarse, API-level)Domain + method restrictions (secrets policy set)
Agent identityIAM roles (instance-level)Cryptographic tokens per agent (agent register)
Process verificationNone (SSRF token-based)keychain-auth daemon (binary hash)
AI agent safetyClient-side guardrails (agent toolkit hook)Infrastructure-enforced (proxy blocks injection)

Using Them Together

If your enterprise mandates AWS Secrets Manager for storage, you can use AgentSecrets as the credential delivery layer. Store secrets in AWS, then configure the AgentSecrets proxy to resolve from AWS and inject at the transport boundary. Your AI agents benefit from zero-knowledge execution without migrating storage.

Was this helpful?
Thanks for your feedback!
Your feedback helps us improve the platform.