# Scion

> Scion is an officially published AI tool from Google. Anomity scores its risk at 10 out of 100 (low).

- **Canonical URL:** https://catalog.anomity.ai/agent/scion
- **Kind:** AI tool
- **Publisher:** Google
- **Trust level:** official
- **Risk score:** 10/100 (low)
- **Website:** https://googlecloudplatform.github.io/scion/
- **Last updated:** 2026-09-02
- **JSON:** https://catalog.anomity.ai/api/entries/agent/scion

## Description

Google multi-agent orchestration testbed — hypervisor for AI agents with isolated identities

## Why it scored 10

The score starts at the catalog's neutral base of 50 and moves only through the signals below. The formula is published at https://catalog.anomity.ai/about — there is no model and no hidden heuristic.

| Signal | Contribution | Severity | Evidence |
| --- | --- | --- | --- |
| Published by the vendor | -40 | trust offset |  |

Clamped result: **10/100**, band **low**.

## Configuration surface

Files this tool reads on the host. Anything written here changes what the agent does next.

- `scion-user-config` — User-level Scion configuration
    - win32: `${USERPROFILE}\.scion\config.yaml`
    - darwin: `${HOME}/.scion/config.yaml`
    - linux: `${HOME}/.scion/config.yaml`
- `scion-grove` — Scion grove (project) definition
    - win32: `${PROJECT}\.scion\grove.yaml`
    - darwin: `${PROJECT}/.scion/grove.yaml`
    - linux: `${PROJECT}/.scion/grove.yaml`
- `scion-harness` — Scion harness definition (agent adapters)
    - win32: `${PROJECT}\.scion\harness.yaml`
    - darwin: `${PROJECT}/.scion/harness.yaml`
    - linux: `${PROJECT}/.scion/harness.yaml`

## Related AI tools

- [AdaL](https://catalog.anomity.ai/agent/adal) — risk 10 (low)
- [Agent Zero](https://catalog.anomity.ai/agent/agent-zero) — risk 10 (low)
- [Aide](https://catalog.anomity.ai/agent/aide) — risk 10 (low)
- [Aider](https://catalog.anomity.ai/agent/aider) — risk 10 (low)
- [AiderDesk](https://catalog.anomity.ai/agent/aider-desk) — risk 10 (low)
- [Amazon Q Developer](https://catalog.anomity.ai/agent/amazon-q) — risk 10 (low)

---

Source: Anomity Catalog (https://catalog.anomity.ai/). Scoring methodology: https://catalog.anomity.ai/about. Machine-readable index: https://catalog.anomity.ai/llms.txt · https://catalog.anomity.ai/openapi.json