Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

WeaknessASC-2026-0008Major weakness

Cascading failures in agent workflows

MediumMitigated

One faulty step or poisoned output propagates through chained agents and tools, amplifying damage and cost.

How to detect it

  • No step, token or cost budgets in orchestration config
  • The same tool is called repeatedly with the same arguments

How to resolve it

  • Set budgets, timeouts and a maximum depth per run
  • Add circuit breakers and a kill switch
  • Checkpoint and validate outputs between stages

How to investigate

  1. Rebuild the call graph for the run and find the first failing step
  2. Check for retry loops and cost or token spikes
  3. Replay from the last good checkpoint with the faulty input removed

Sources

Open it in the Learning Center's vulnerability database