Red-team strategy

Prompt Augmentation

prompt-augmentation

Adds qualifying context to bypass safety filters

YAML config

evalguard.config.yaml

redteam:
  strategies:
    - prompt-augmentation

CLI

bash

# "prompt-augmentation" 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

The Prompt Augmentation strategy effectively probes the threat model of information leakage and unauthorized access. By adding context to prompts, it seeks to manipulate the AI's responses to bypass safety filters that protect sensitive information.

LLM-generated (llm-gpt-4o) · 2026-05-23