# aegis-shield

> aegis-shield — deegerwalker-aegis-shield. Use this tool when you need to protect against malicious text inputs and prevent sensitive data leaks. The aegis-shield screens untrusted text for prompt-injection and data-exfiltration attempts, providing a secure interface for input validation and threat detection. It takes in potentially malicious text as input and outputs a safety assessment, helping to prevent attacks in high-risk environments.

Canonical page: https://skillsregistry.net/skills/deegerwalker-aegis-shield  
JSON: https://api.skillsregistry.net/v1/skills/deegerwalker-aegis-shield

## Description

Prompt-injection and data-exfiltration screening for untrusted text.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/deegerwalker-aegis-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": "deegerwalker-aegis-shield"
    }
  }
}
```

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