# BlindOracle

> Use this tool when you need to conduct comprehensive security audits for AI agents, covering all 10 OWASP Agentic Security categories. BlindOracle solves problems related to AI agent security and trust, providing a robust framework for evaluating and ensuring the security of AI systems. It takes in AI agent configurations and outputs a detailed audit score, making it ideal for use cases where security and trust are paramount, such as in decentralized economies and federated AI systems.

Canonical page: https://skillsregistry.net/skills/craigmbrown-blindoracle-mcp  
JSON: https://api.skillsregistry.net/v1/skills/craigmbrown-blindoracle-mcp

## Description

Unchallengeable AI agent security audits. MASSAT framework covers all 10 OWASP Agentic Security categories (ASI01-ASI10); audit score 4.3/10 published publicly. Plus the trust layer for the x402 agent economy: ERC-8004 passports, ProofDB delegation chains, on-chain anchoring, x402 + Fedimint payments. Apache-2.0.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ivhvgjrxbj)
- **Repository:** <https://github.com/craigmbrown/blindoracle-mcp>

## 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": "craigmbrown-blindoracle-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/craigmbrown-blindoracle-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/craigmbrown-blindoracle-mcp/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