# Mobile Agent Guardian

> Mobile Agent Guardian — salus-ryan-mobile-agent-guardian. Use this tool when you need to ensure secure and reliable control of mobile agents, such as robots or drones, by providing a layered safety and verification system. It solves problems related to trust and accountability in autonomous systems by utilizing vision classification, verify-after-act loops, and cryptographic anchoring. This tool is ideal for applications requiring high levels of security and auditability, such as industrial automation or surveillance, with inputs including visual data and control commands, and outputs providing verified and secure control signals.

Canonical page: https://skillsregistry.net/skills/salus-ryan-mobile-agent-guardian  
JSON: https://api.skillsregistry.net/v1/skills/salus-ryan-mobile-agent-guardian

## Description

A five-level safety and verification layer for embodied mobile agents that provides auditable, secure phone control through vision classification, verify-after-act loops, and cryptographic anchoring.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dlncz91qpf)
- **Repository:** <https://github.com/salus-ryan/mobile-agent-guardian>

## 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": "salus-ryan-mobile-agent-guardian"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/salus-ryan-mobile-agent-guardian` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/salus-ryan-mobile-agent-guardian/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