Cascading failure across agents and systems
One agent's or system's error spreads through the agents and systems connected to it.
NIST AI 600-1 · Value Chain and Component IntegrationOWASP Agentic ASI08FSB agentic AI consultation (2026)
1incidents (primary) · 1 more as secondary
0read for controls · 1 not yet
0fixes reported
0repeats after a fix
Incidents per month
No rise: 0 in Oct 2026, against an average of 0 over the 3 months before.
Developers
Developer not named in the sources.
Where the chain broke
| Part of the system | Incidents where the control was not effective or did not exist | Incidents where the control was effective | Incidents where sources don't mention the control | Incidents not yet checked for controls |
|---|---|---|---|---|
| L1 Model Model provider | 1 | |||
| L2 Harness Agent framework vendor | 1 | |||
| L3 Application Deployer | 1 | |||
| L4 Infrastructure / target Organisation hit | 1 |
Controls for this risk, by layer
| Control | Incidents where the control was not effective or did not exist | Incidents where the control was effective | Incidents where sources don't mention the control | Most common reason it was not effective |
|---|---|---|---|---|
| Stop control L2 Harness | ||||
| Fail-closed defaults L2 Harness | ||||
| Controls on agent-to-agent messages L2 Harness | ||||
| Rate and spend limits L3 Application | ||||
| Undo for agent actions L3 Application | ||||
| Segmentation of agent components L3 Application | ||||
| Circuit breakers L3 Application |
7 of 7 controls for this risk not yet recorded as effective.
Fixes reported and what followed
No remediation reported for incidents of this risk.
Incidents
EffectiveNot effectiveNot effective (bypassed)Did not existNot stated in sourcesNot yet checkedAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Where it failed | Controls mentioned in sources |
|---|---|---|---|---|
| 2026-06-04 | GitHub outage caused by AI-driven traffic surge and configuration error | Cascading failure across agents and systems | Not yet checked |
Also under this risk as a secondary risk: LR-2026-0725