# com.dustforge/demipass

> com.dustforge/demipass — com-dustforge-demipass. Use this tool when you need to securely manage credentials for agents, keeping sensitive information blind to the application context. It solves problems of credential exposure and misuse by handling secrets for ssh, http, smtp, git, and db connections without revealing them. The demipass tool accepts credential inputs and outputs secure, blinded access to protected resources.

Canonical page: https://skillsregistry.net/skills/com-dustforge-demipass  
JSON: https://api.skillsregistry.net/v1/skills/com-dustforge-demipass

## Description

Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 2.5.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-09-02

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.dustforge%2Fdemipass)
- **Repository:** <https://github.com/bildow/demipass>

## 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": "com-dustforge-demipass"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-dustforge-demipass` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-dustforge-demipass/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