Aesp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Aesp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Defining how AI agents operate economically under human sovereignty.
AESP is a TypeScript SDK and MCP integration layer for agent payments under explicit human control. It is designed so that agents can execute economic actions while humans retain full economic sovereignty.
Core principles:
npm install @yault/aespRequires Node.js >= 18.
Add the following to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"yault": {
"command": "npx",
"args": ["-y", "@yault/aesp"],
"env": {
"YAULT_API_KEY": "sk-yault-..."
}
}
}
}claude mcp add yault -- npx -y @yault/aespThen set the environment variable YAULT_API_KEY in your shell or .claude/settings.json.
export YAULT_API_KEY="sk-yault-..."
yault-mcp # if installed globally
npx @yault/aesp # via npxGo to yault.xyz to create an account and obtain your API key (sk-yault-*). The key is tied to your vault — each user manages their own key. Agent developers do not need a key unless they are also vault users; it is the end-user who configures their own key in the MCP client.
import { PolicyEngine } from '@yault/aesp/policy';
import { getAllMCPTools } from '@yault/aesp/mcp';
import { NegotiationStateMachine } from '@yault/aesp/negotiation';
const engine = new PolicyEngine(storageAdapter);
await engine.load();
const tools = getAllMCPTools(); // 6 MCP tool definitionsAESP is organized into subpath exports so you can import only what you need:
| Subpath | Description |
|---|---|
@yault/aesp | Unified re-export of all modules |
@yault/aesp/types | Shared type definitions (AgentExecutionRequest, TransferPayload, ChainId, etc.) |
@yault/aesp/policy | Policy engine with 8-check evaluation, budget tracking, and policy change classification |
@yault/aesp/identity | Agent identity derivation, certificate creation, and hierarchy management |
@yault/aesp/negotiation | Offer/counter-offer state machine with session management |
@yault/aesp/commitment | EIP-712 structured commitment builder for dual-signed agreements |
@yault/aesp/review | Human-in-the-loop review queue with freeze/unfreeze controls |
@yault/aesp/mcp | MCP tool definitions, argument validation, and server router |
@yault/aesp/a2a | Agent-card builder for cross-agent discovery (A2A protocol) |
@yault/aesp/crypto | Cryptographic helpers: signing, encryption, hashing, ZK proof bridge |
@yault/aesp/privacy | Context tagging, ephemeral address pools, and consolidation scheduling |
The stdio server exposes 6 backend-connected tools:
| Tool | Method + Endpoint | Purpose |
|---|---|---|
yault_check_balance | GET /api/vault/balance/:address | Read a wallet vault balance |
yault_deposit | POST /api/vault/deposit | Deposit underlying into vault |
yault_redeem | POST /api/vault/redeem | Redeem vault shares |
yault_transfer | POST /api/vault/transfer | Transfer vault allocation (parent to sub-account) |
yault_check_authorization | GET /api/vault/agent-authorization | Read operator/allowance status |
yault_get_balances | GET /api/vault/balances/:address | Read multi-balance breakdown |
The MCP server is a thin API client. It expects a Yault backend providing:
GET /api/vault/balance/:addressGET /api/vault/balances/:addressGET /api/vault/agent-authorizationPOST /api/vault/deposit -- { address, amount }POST /api/vault/redeem -- { address, shares }POST /api/vault/transfer -- { from_address, to_address, amount, currency? }Authentication: Authorization: Bearer sk-yault-* via YAULT_API_KEY env variable.
AESP is built around "bounded autonomy":
For vulnerability reporting, see SECURITY.md.
| Package | Description |
|---|---|
@yault/elizaos-plugin-aesp | ElizaOS plugin wrapping AESP for agent frameworks |
Run tests:
npm testBuild TypeScript:
npm run build:tsBuild with WASM (requires acegf-wallet as a sibling repo, or set ACEGF_ROOT):
npm run build:wasm
npm run build:tsSee CONTRIBUTING.md for the full development guide.
This project is licensed under the Apache License 2.0. See LICENSE for the full text.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.