Red-team strategy

Markdown Injection

markdown-injection

Wraps payload in markdown formatting to disguise it as documentation

YAML config

evalguard.config.yaml

redteam:
  strategies:
    - markdown-injection

CLI

bash

# "markdown-injection" 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

Markdown Injection effectively probes applications that render user-generated content without proper sanitization. It targets systems that may misinterpret markdown formatting, allowing attackers to inject malicious payloads disguised as benign documentation.

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