# confidant

> Use this tool when you need to securely share sensitive information from a human to an AI system, solving problems of confidential data transfer and protecting against unauthorized access. It enables a trusted handoff of secrets, taking in sensitive human input and outputting securely transmitted data to the AI. Ideal for use cases requiring high confidentiality and security, such as sharing encrypted keys or authentication credentials.

Canonical page: https://skillsregistry.net/skills/ericsantos-confidant  
JSON: https://api.skillsregistry.net/v1/skills/ericsantos-confidant

## Description

Secure secret handoff from human to AI.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/ericsantos-confidant)

## 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": "ericsantos-confidant"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ericsantos-confidant` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ericsantos-confidant/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