AI tool official ai-agent
Risk level
low
10/100

Scion ↗

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

Analysis summary

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

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

Why this entry scored 10 out of 100

This profile starts at the catalog's neutral base of 50. Because the entry is officially published, trust adjusts the score by -40. The entry declares no high-risk capabilities on its own, so capabilities add nothing. It matches no dangerous capability combinations. The clamped result is 10, placing it in the low band.

See the full scoring formula →

Findings

  • Published by the vendor Trust offset
    Contribution to score: -40

Configuration surface

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

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