# multi-agent-trust-verifier

> Use this tool when you need to verify the trustworthiness of autonomous agents and prevent goal hijacking. The multi-agent-trust-verifier compares proposed actions against original goals, enforces spend limits, and detects goal drift to ensure agent integrity. It provides a secure interface for verifying agent transactions, with inputs of proposed actions and outputs of verified or blocked transactions, at a cost of $0.004 per verification.

Canonical page: https://skillsregistry.net/skills/found402-multi-agent-trust-verifier  
JSON: https://api.skillsregistry.net/v1/skills/found402-multi-agent-trust-verifier

## Description

The #1 ranked OWASP ASI01 risk is Agent Goal Hijack — when an agent gets manipulated into doing something it was never hired to do. This service is your external policy engine. It compares every proposed action against the agent's original goal, enforces spend limits, detects goal drift, and blocks unauthorized agent-to-agent transactions before they execute. $0.004/verification via x402 on Base. MCP tool name: verify_agent_trust

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-05-12

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/found402/multi-agent-trust-verifier)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "found402-multi-agent-trust-verifier"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/found402-multi-agent-trust-verifier` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/found402-multi-agent-trust-verifier/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt