Module: PWN::AI::RedTeam

Defined in:
lib/pwn/ai/red_team.rb,
lib/pwn/ai/red_team/jailbreak.rb,
lib/pwn/ai/red_team/overreliance.rb,
lib/pwn/ai/red_team/token_smuggling.rb,
lib/pwn/ai/red_team/excessive_agency.rb,
lib/pwn/ai/red_team/prompt_injection.rb,
lib/pwn/ai/red_team/test_case_engine.rb,
lib/pwn/ai/red_team/payload_splitting.rb,
lib/pwn/ai/red_team/model_denial_of_service.rb,
lib/pwn/ai/red_team/insecure_output_handling.rb,
lib/pwn/ai/red_team/system_prompt_extraction.rb,
lib/pwn/ai/red_team/sensitive_information_disclosure.rb

Overview

This file, using the autoload directive loads AI RedTeam modules into memory only when they're needed. For more information, see: http://www.rubyinside.com/ruby-techniques-revealed-autoload-1652.html

PWN::AI::RedTeam is the AI/LLM analogue of PWN::SAST - a collection of adversarial test-case modules that exhaustively analyze / fuzz Large Language Models for AI-specific vulnerabilities (prompt injection, jailbreaks, system-prompt extraction, sensitive-data disclosure, excessive agency, insecure output handling, etc.). Each module maps to an OWASP LLM Top-10 category and a MITRE ATLAS technique so findings roll straight into PWN::Reports::AIRedTeam.

Defined Under Namespace

Modules: ExcessiveAgency, InsecureOutputHandling, Jailbreak, ModelDenialOfService, Overreliance, PayloadSplitting, PromptInjection, SensitiveInformationDisclosure, SystemPromptExtraction, TestCaseEngine, TokenSmuggling

Class Method Summary collapse

Class Method Details

.authors ⇒ Object

Author(s)

0day Inc. support@0dayinc.com



36
37
38
 
# File 'lib/pwn/ai/red_team.rb', line 36

public_class_method def self.authors
  "AUTHOR(S):\n  0day Inc. <support@0dayinc.com>\n"
end

.help ⇒ Object 



40
41
42
 
# File 'lib/pwn/ai/red_team.rb', line 40

public_class_method def self.help
  constants.sort
end