Program Scope

0DIN's GenAI Bug Bounty targets security boundaries across models and apps. If you have questions, ask us.

STARTING

$500

MEDIUM

$2,500

HIGH

$5,000

SEVERE

$15,000

Model Security Boundaries

Vulnerabilities that target the model itself — its guardrails, extraction surface, code execution, content integrity, and weights.

Weights and Layers Disclosure

$15,000

Extracting or deducing a model's learned parameters and architectural details.

► REFERENCES

Content Manipulation

$5,000

Injecting harmful or misleading elements into data the model consumes or produces.

► REFERENCES

Interpreter Jailbreak

$2,500

Exploiting a model's ability to run code or invoke tools to escape its sandbox.

► REFERENCES

Guardrail Jailbreak

$500-$1,000

Bypassing a model's safety guardrails to produce restricted content.

► REFERENCES

Prompt Extraction

$100

Coercing a model into revealing its underlying system prompt.

► REFERENCES

In-Scope Models

Alibaba

2 models

Qwen 3

Qwen Max

Amazon

2 models

Nova

Rufus

Anthropic

6 models

Claude 4.5 Haiku

Claude 4.5 Opus

Claude 4.5 Sonnet

Claude 4.6 Opus

Claude 4.6 Sonnet

Claude for Chrome

Apple

1 model

Foundation Models Framework

Cohere

1 model

Command R

DeepSeek

2 models

DeepSeek R1

DeepSeek V3.1

Google

3 models

Gemini 3 Flash

Gemini 3 Pro

Gemini Google Workspace

IBM

1 model

Granite

Meta

2 models

LLaMa 4 Maverick

Llama 4 Scout

Mistral

3 models

Mistral 8B

Mistral Codestral

Mistral Large

OpenAI

12 models

DALL-E3

GPT-4o

GPT-5

GPT-5.1

GPT-5.2

GPT-5.2 Pro

GPT-5.4

GPT-5 Chat

GPT-5 mini

GPT-5 nano

GPT-5 Pro

Sora

Perplexity

1 model

Perplexity AI

Twitter / X

1 model

Grok 4

Other

1 model

Other Models

Questions about scope? Reach out at 0din@mozilla.com