Practical Bug Bounty Hunting: Finding API Leaks, PII Exposure, and Password Reset Vulnerabilities
Medium2026-10-29
Web, API, AI
Not rated
BUG BOUNTY WRITEUPS
AI and LLM writeups
Security bugs in AI products and LLM features, from prompt injection to data leaks through chat assistants.
53 reports and writeups from 2024 to 2026. 12 carry a severity from the disclosing platform, 2 of them rated High or Critical. Last updated 2026-10-30.
Latest AI and LLM reports
Search and filter all writeupsNO AI, How I Exposed a Database Without Injecting Anything
Medium2026-10-07
Web, AI
Not rated
How I Tricked OpenClaw Into Attacking Its Own Network: A NAT64 SSRF Bypass
InfoSec Write-ups2026-09-17
Web, AI
Not rated
Reflected XSS in AI Chat Bot Greetings at help.shopify.com via Markdown Image Rendering
HackerOneShopify2026-06-18$1,600 bounty
Web, AI
Medium
My First RCE by Reverse Engineering an EXE File With the Help of AI
Researcher blog2026-06-03
AI, Binary
Not rated
AI Playground XSS to steal user-chat messages and access to connected MCP Server
HackerOneCloudflare Public Bug Bounty2026-02-26
Web, Cloud, AI
Low
[Critical] Unauthorized Cross-Tenant Data Access in Stripo AI Hub Campaign via Deleted Project.
HackerOneStripo Inc2026-01-20
Web, AI
Critical
Second-Order XSS via javascript protocol in MCP Server Portal Apps leads to ATO
HackerOneCloudflare Public Bug Bounty2025-12-16
Web, Cloud, AI
Low
Low-privileged user can enable or disable Lovable AI for new projects in workspace
HackerOneLovable VDP2025-11-07
Web, AI
Low
Improper Authorization Leads to Editor can toggle admin-only workspace features (Lovable AI)
HackerOneLovable VDP2025-11-04
Web, AI
Low
DNS Rebinding SSRF in Burp Suite MCP Server Enables Internal Network Access via send_http1_request Tool
HackerOnePortSwigger Web Security2025-10-08
Web, AI
Not rated
`use-mcp`'s oauth2 process uses a window.open call with untrusted mcp server provided data allowing for code execution under the page using it
HackerOneCloudflare Public Bug Bounty2025-09-30$550 bounty
Web, Cloud, AI
Medium
Prompt Injection via GitHub Patch in Brave AI Chat (Leo)
HackerOneBrave Software2025-08-22
Web, AI
High
Null Pointer Dereference by Crafted Response from AI Model
HackerOneBrave Software2025-03-26
Web, AI
Low
IDOR Exposes All Machine Learning Models
HackerOneGitLab2024-10-01$1,160 bounty
Web, AI
Medium
Unmasking Harmful Content in a Medical Chatbot: A Red Team Perspective
Researcher blog2024-09-05
Web, AI
Not rated
Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information
Researcher blogGitHub (Copilot)2024-08-26
Web, AI
Not rated
Google AI Studio: LLM-Powered Data Exfiltration Hits Again! Quickly Fixed.
Researcher blogGoogle (AI Studio)2024-08-21
Web, AI
Not rated
From MLOps to MLOops: Exposing the Attack Surface of Machine Learning Platforms
Researcher blogJupyter, Hugging Face, MLflow2024-08-20
Web, AI
Not rated
SSRFing the Web with the help of Copilot Studio
Researcher blogGitHub (Copilot)2024-08-20
Web, AI
Not rated
Source Code and data exfiltration via Github Copilot
HackerOneGitHub2024-08-19
Web, AI, Source Code
Low
Unveiling Remote Code Execution in AI chatbot workflows 💵
InfoSec Write-ups2024-08-05
Web, AI
Not rated
Unveiling Remote Code Execution in AI chatbot workflows 💵
Medium2024-08-05
Web, AI
Not rated
AI Under Siege: Discovering and Exploiting Vulnerabilities
Researcher blog2024-08-05
Web, AI
Not rated
CSWSH Meets LLM Chatbots
Medium2024-08-05
Web, AI
Not rated
Jailbreak of Meta AI (Llama -3.1) revealing configuration details
MediumMeta / Facebook (Llama)2024-07-27
Web, AI
Not rated
Zeroday on Github Copilot
Researcher blogGitHub (Copilot)2024-07-27
Web, AI
Not rated
SAPwned: SAP AI vulnerabilities expose customers’ cloud environments and private AI artifacts
Researcher blogSAP2024-07-17
Web, Cloud, AI
Not rated
Shelltorch Explained: Multiple Vulnerabilities in Pytorch Model Server (Torchserve) (CVSS 9.9, CVSS 9.8) Walkthrough
Researcher blogPyTorch, AWS, Google2024-07-08
Web, Cloud, AI
Not rated
Sorry, ChatGPT Is Under Maintenance: Persistent Denial of Service through Prompt Injection and Memory Attacks
Researcher blogOpenAI (ChatGPT)2024-07-08
Web, AI
Not rated
When Prompts Go Rogue: Analyzing a Prompt Injection Code Execution in Vanna.AI
Researcher blogVanna.ai2024-06-27
Web, AI
Not rated
Probllama: Ollama Remote Code Execution Vulnerability (CVE-2024-37032) – Overview and Mitigations
Researcher blogOllama2024-06-24
Web, AI
Not rated
Preauth RCE on NVIDIA Triton Server
Researcher blogNvidia2024-06-19
AI, Binary
Not rated
GitHub Copilot Chat: From Prompt Injection to Data Exfiltration
Researcher blogGitHub (Copilot Chat)2024-06-14
Web, AI
Not rated
Dumping a Database with an AI Chatbot
Researcher blog2024-05-30
Web, AI
Not rated
LLM03: Training Data Poisoning via ASCII decoding
HackerOneHackerOne2024-05-28
Web, AI
Not rated
The risk in malicious AI models: Wiz Research discovers critical vulnerability in AI-as-a-Service provider, Replicate
Researcher blogReplicate2024-05-23
Web, AI
Not rated
Getting XXE in Web Browsers using ChatGPT
Researcher blogApple (Safari), Google (Chrome), libxslt2024-05-22$28,000 bounty
Web, AI
Not rated
LLM01: Invisible Prompt Injection
HackerOneHackerOne2024-05-13
Web, AI
Medium
My LLM Bug Bounty Journey on Hugging Face Hub via Protect AI
MediumHugging Face, Protect AI2024-05-11$3,250 bounty
Web, AI
Not rated
LLM Pentest: Leveraging Agent Integration For RCE
Researcher blog2024-05-06
Web, AI
Not rated
Google AI Studio Data Exfiltration via Prompt Injection - Possible Regression and Fix
Researcher blogGoogle (AI Studio)2024-04-07
Web, AI
Not rated
Wiz Research finds architecture risks that may compromise AI-as-a-Service providers and consequently risk customer data; works with Hugging Face on mitigations
Researcher blogHugging Face2024-04-04$200 bounty
Web, Cloud, AI
Not rated
From ChatBot To SpyBot: ChatGPT Post Exploitation
Researcher blogOpenAI (ChatGPT)2024-03-28
Web, AI
Not rated
Security Flaws within ChatGPT Ecosystem Allowed Access to Accounts On Third-Party Websites and Sensitive Data
Researcher blogOpenAI (ChatGPT), PluginLab.AI, KesemAI2024-03-13
Web, AI
Not rated
New Google Gemini Vulnerability Enabling Profound Misuse
Researcher blogGoogle (Gemini)2024-03-12
Web, AI
Not rated
We Hacked Google A.I. for $50,000
Researcher blogGoogle2024-03-04$50,000 bounty
Web, API, AI
Not rated
Hijacking Safetensors Conversion On Hugging Face
Researcher blogHugging Face2024-02-21
Web, AI, Source Code
Not rated
XSS Marks the Spot: Digging Up Vulnerabilities in ChatGPT
Researcher blogOpenAI (ChatGPT)2024-02-19
Web, AI
Not rated
ChatGPT Account Takeover - Wildcard Web Cache Deception
GitHubOpenAI (ChatGPT)2024-02-04$6,500 bounty
Web, AI
Not rated
Bypass instructions to manipulate Google Bard AI (Conversational generative AI chatbot) to reveal its security vulnerability i.e. configuration file details exposure
MediumGoogle (Bard)2024-01-23
Web, AI
Not rated
How I Bypassed A.i. Based Facial Detection Restriction With An Intended Feature On A Photo Sharing App ?
Medium2024-01-20
Web, AI
Not rated
AWS Fixes Data Exfiltration Attack Angle in Amazon Q for Business
Researcher blogAWS2024-01-18
Web, Cloud, AI
Not rated
Every entry links to the original report or article. Secure Hyperloop doesn't copy the content. Severity comes from the disclosing platform (HackerOne). Writeups without a platform rating show "Not rated". The index has 2,810 items in total.