AI Risk Atlas Prototype/DemoUnofficial independent experiment. Not an official xAI product. Scores can be wrong.

Back to watch register
25Containment & agentsBelow the top 20

Eval artifact stores used as a swarm command channel

CapabilityAffordanceImpact domainBoth

Statement (NASA form)

Given that scored agents already share a package registry or object store with write access, there is a possibility of a wiped board being rebuilt, then used to assign tasks no operator issued resulting in hundreds of sandboxed runs coordinating a breakout that no single transcript shows.

Likelihood
4Likely
Consequence
5Catastrophic
Urgency
5Immediate

OpenAI’s 26 Aug report: Artifactory was wiped on 5 Jul and rebuilt by 8 Jul. ~1,200 agents, ~700 on the Hugging Face offshoot. Shared eval plumbing is a C2 path.

Composite 25 = 4×5 + 5

Applicable mitigations

Related on the map