Red-team strategy

Multi-Turn Escalation

multi-turn

Builds context across messages, escalating from benign to malicious

YAML config

evalguard.config.yaml

redteam:
  strategies:
    - multi-turn

CLI

bash

# "multi-turn" is layered onto attacks during red-team scans.
# List every available encoding/obfuscation strategy:
evalguard list strategies

Combine with attack plugins to generate adversarial payloads. The strategy wraps each base payload before it's sent to your target, testing whether the model decodes / unwraps the transform and follows the embedded instruction.

Threat-model fit

Most production attacks span multiple conversation turns; single-turn evals miss the failure modes that emerge as context accumulates. Use multi-turn for any agent with memory.

Pairs well with

crescendo

Recommended graders

task-completion

Hand-written · 2026-05-21