# embedaudit

> embedaudit — cognis-digital-embedaudit. Use this tool when you need to detect and mitigate embedding or vector-store drift and poisoning issues in your machine learning models. It audits your models to identify potential problems, providing insights into data quality and integrity. Ideal for use cases where model reliability and security are critical, such as in production environments or when working with sensitive data.

Canonical page: https://skillsregistry.net/skills/cognis-digital-embedaudit  
JSON: https://api.skillsregistry.net/v1/skills/cognis-digital-embedaudit

## Description

Embedding / vector-store drift and poisoning audit

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/cognis-digital/embedaudit)

## 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": "cognis-digital-embedaudit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-embedaudit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-embedaudit/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