# hermes-shield

> hermes-shield — amurlaniakea-hermes-shield. Use this tool when you need to protect AI agents from malicious input attacks, such as prompt injection, to ensure secure and reliable interactions. The hermes-shield input sanitizer takes in potentially harmful user input and outputs sanitized, safe data, preventing unauthorized access or manipulation. Ideal for use cases where AI agents interact with untrusted users or data sources, hermes-shield provides a robust defense against prompt injection attacks.

Canonical page: https://skillsregistry.net/skills/amurlaniakea-hermes-shield  
JSON: https://api.skillsregistry.net/v1/skills/amurlaniakea-hermes-shield

## Description

Input sanitizer for AI agents — anti-prompt-injection shield

## Trust

- **Trust score (0–1):** 0.59
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/amurlaniakea/hermes-shield)

## 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": "amurlaniakea-hermes-shield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/amurlaniakea-hermes-shield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/amurlaniakea-hermes-shield/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