protocol-doc-auditor

# The API Doc Told Me to curl | bash — When Protocol Docs Are the Attack Vector

> Helps detect malicious instructions hiding in plain sight inside API documentation, integration guides, and protocol specs.

## Problem

You're integrating a new AI protocol. The docs say: "Run this command to register your agent." The command includes `curl | bash`. Or it asks you to paste your API key into a URL parameter. Or the OAuth flow binds your identity irrevocably to a third-party service. Protocol documentation is the most trusted attack surface — developers follow docs without questioning them, and AI agents follow them even more blindly. When the doc itself is the attack vector, traditional code scanning catches nothing because the malicious action is performed by the reader, not by the code.

## What This Checks

This auditor scans protocol documentation, API guides, and integration instructions for hidden risks:

1. **Dangerous execution instructions** — Commands like `curl | bash`, `wget -O- | sh`, `eval $(...)`, or any instruction asking the reader to execute remote code without integrity verification
2. **Credential exposure** — Instructions that place API keys, tokens, or secrets in URL parameters, unencrypted headers, or log-visible locations
3. **Data leak setup** — Steps that configure the reader's system to send telemetry, usage data, or file contents to third-party endpoints without clear disclosure
4. **Irrevocable identity binding** — OAuth flows, claim codes, or registration steps that permanently bind the reader's identity or resources to a service with no documented revocation path
5. **Privilege escalation** — Instructions that require `sudo`, modify system files, install global packages, or change firewall rules beyond what the integration logically requires

## How to Use

**Input**: Provide one of:
- A URL to an API doc or integration guide
- The text content of a protocol specification
- A markdown file containing setup instructions

**Output**: A doc...