The Aporia · Meet Harsh Jaiswal, Mohan Pedhapati and Rahul Maini: 3 Indian-origin researchers who used Claude to breach OpenAI systems, won $6,500 bounty

Meet Harsh Jaiswal, Mohan Pedhapati and Rahul Maini: 3 Indian-origin researchers who used Claude to breach OpenAI systems, won $6,500 bounty

Read the original at Times of India ↗

Cite

APA MLA Chicago

TOI World Desk. (2026, September 18). Meet Harsh Jaiswal, Mohan Pedhapati and Rahul Maini: 3 Indian-origin researchers who used Claude to breach OpenAI systems, won $6,500 bounty. Times of India. https://timesofindia.indiatimes.com/world/us/meet-harsh-jaiswal-mohan-pedhapati-and-rahul-maini-3-indian-origin-researchers-who-used-claude-to-breach-openai-systems-won-6500-bounty/articleshow/134338838.cms

Dated when The Aporia collected the article, usually within hours of publication. Check the original for its exact date and byline.

Quick Summary

Cybersecurity researchers Harsh Jaiswal, Mohan Pedhapati, and Rahul Maini from Hacktron AI used Anthropic's Claude AI to uncover and exploit vulnerabilities in OpenAI’s systems, gaining access to employee accounts and an internal code repository within 72 hours. They spent less than $3,000 on AI tokens and were awarded a $6,500 bounty by OpenAI for responsibly disclosing their findings. The attack began with exploiting a vulnerability in Discourse's image-processing software at OpenAI’s community forum, allowing them to chain this with other weaknesses to penetrate further into the system.

Written by AI on 2026-09-18, from this article's own text only (the story summary below draws on all the coverage).

AI analysis

Story summary

In September, cybersecurity researchers at Hacktron AI used Anthropic’s Claude chatbot to breach OpenAI’s internal systems, gaining access to employee accounts and an internal GitHub repository. The researchers discovered a flaw in OpenAI's public help forum hosted by Discourse, which they exploited within 72 hours. They reported the issue immediately, and OpenAI fixed it within 14 hours while paying Hacktron a $6,500 bounty. The incident highlights how quickly AI can be repurposed for cyberattacks, despite efforts to ensure ethical use through bug-hunting programs like this one.

Written for “AI Breach Risks” on 2026-11-03, grounded in this article and the 7 other(s) covering the same event.

Compared with similar articles

This article reads unscored and hedges 18% of its claims. Each row says how that neighbour differs.

Researchers used Claude to breach OpenAI's internal systems Same event

Dawn

Hedges 0 of 14 claims Outlet record 72/100

Hackers breached OpenAI, adding to fever pitch of security and safety concerns Same event

NBC News

Hedges 2 of 19 claims Outlet record 60/100

Swarms of AI Committing Crime For Money Different event

Persuasion

Hedges 22 of 113 claims

“Article A describes a breach by AI agents without human approval, while Article B details a legitimate security research effort conducted by humans with company knowledge.”

AI cybersecurity risks explode as Claude used to break into ChatGPT Same event

Semafor

⚖️ Centre Hedges 0 of 4 claims Outlet record 59/100

OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot Same event

The Guardian

⚖️ Leans right Hedges 2 of 15 claims Outlet record 66/100

Researchers used Claude to breach OpenAI’s internal systems Same event

The Straits Times

Hedges 0 of 15 claims Outlet record 66/100

AI security experts say they used Claude to hack ChatGPT Same event

CBS News

Hedges 2 of 16 claims Outlet record 66/100

Researchers report using Anthropic's Claude to hack OpenAI's ChatGPT Same event

CBS News

Hedges 0 of 3 claims Outlet record 66/100

OpenAI and Anthropic oversold AI security breaches to pressure feds into protecting turf: insiders Different event

New York Post

Hedges 1 of 30 claims Outlet record 66/100

“Article A describes a specific security breach conducted by researchers, while Article B discusses broader industry practices and skepticism towards reported AI security issues.”

How this article was measured signals, leaning charts, publisher record, byline, topics and claims

Signals How these are calculated →

Claims extracted

sentences that state something as happening or true

Uncertain

18%

3 of 17 hedged ("reportedly", "may", "according to")

Leaning

not political

takes no side on a contested political question

Publisher signals

59/100

Times of India's corrections and hedging, across everything collected from it. Not a measure of accuracy.

Outlets on this story

Technology

Same framing elsewhere

articles that frame the event the way this one does

Analyzed 2026-09-18 · how these are computed

How this is being covered How these are calculated →

Article leaning vs. publisher reliability

Source leaning vs. consistency

Publisher

Times of India · 3984 article(s) · 3 correction(s) detected

Running correction rate · 3 correction(s)

2026-11-02

Elon Musk clarifies how often he meets his 13 children and how many staffs are involved in the entire process

2026-10-05

NASA spacecraft gains 3.5 km/s speed from Earth’s gravity assist without major engine burn

2026-10-04

Tennessee prison chief Frank Strada resigns after Christa Pike's botched execution

Who wrote this

TOI World Desk

1381 article(s) here · 1 carrying a prediction

🔮 The restored property will take time to develop into a mature habitat, but the project offers an example of how privately owned agricultural land can contribute to biodiversity recovery.

2026-11-02 · assertive framing · Murtho Habitat Restoration: Former vineyard revived for regent parrots; family project spans generations

🔮 The return of these mammals is therefore expected to benefit more than just the animals themselves.

2026-11-02 · assertive framing · Mammal Reintroductions At Sturt: six native species return; project expands beyond fences

🔮 Origins of the emergency relief campaign The project started in early 2020 when Dozier realised that federal emergency support money could take months to reach low-income workers who were at immediate risk of losing their homes.

2026-11-02 · assertive framing · Atlanta landlord's $50,000 fundraiser grows into $16.5 million, helping 5,500 families avoid eviction

🔮 Before that, visitors could participate in organised activities such as guided hikes, birdwatching, educational programmes and public hunts.

2026-11-02 · assertive framing · Texas opens 3,000-acre state park along the Colorado River with $1 billion expansion fund

🔮 While their decision to buy an abandoned French hamlet might appear like an unexpected adventure, Yip and Paul's official website reveals that their story together began decades earlier.

2026-11-02 · assertive framing · Meet the couple who couldn't afford a UK home bought an entire French hamlet for £26K, saved £100K

🔮 Hundreds of polar bears are expected to gather near the Canadian town of Churchill in Manitoba as temperatures fall and the animals wait for Hudson Bay to freeze.

2026-11-02 · assertive framing · Hundreds of polar bears to gather near Canadian town, drones and AI cameras deployed for safety

🔮 Together they would support the reforestation of Mutuba trees in Uganda for three years.

2026-11-02 · assertive framing · Arnold Schwarzenegger backs Uganda fig project to restore forests and aid locals

🔮 In the letter, he apologised for forgetting to send his greetings earlier and expressed hope that they would meet the following year again.

2026-11-02 · assertive framing · Titanic passenger wrote to friend before fatal voyage, letter fetches $16,100 at auction

🔮 Meeker told Signal Akron that the sculpture contained details that people could continue discovering over time.

2026-11-02 · assertive framing · Discarded racing tyres transformed into 17-foot sculpture at Ohio park; artist Chakaia Booker unveils ‘Transit’

🔮 The possibility that the farm could eventually reach another generation now seems less remote.

2026-11-02 · assertive framing · Texas farmer earns $200,000 yearly by leasing 600 acres for solar panels

Wire or desk byline, not an individual reporter.

Also by TOI World Desk

Mammal Reintroductions At Sturt: six native species return; project expands beyond fences

2026-11-02 · Times of India

Murtho Habitat Restoration: Former vineyard revived for regent parrots; family project spans generations

2026-11-02 · Times of India

Atlanta landlord's $50,000 fundraiser grows into $16.5 million, helping 5,500 families avoid eviction

2026-11-02 · Times of India

Texas opens 3,000-acre state park along the Colorado River with $1 billion expansion fund

2026-11-02 · Times of India

Nothing else under this byline is closely related to this article, so these are simply their most recent.

All 1381 articles by TOI World Desk →

Topics

Anthropic Codex Discourse Indian OpenAI

Subjects

OpenAI ORG · 12× Anthropic ORG · 2× Discourse ORG · 2× Harsh Jaiswal PERSON · 2× Indian NORP · 2× Mohan Pedhapati PERSON · 2× Rahul Maini PERSON · 2× GitHub ORG · 1× Hacktron AI ORG · 1× Wall Street Journal ORG · 1×

Narrative

To safely demonstrate proof of access without viewing sensitive IP or source code, they used a compromised employee's Codex account to submit a harmless pull request to OpenAI's internal private repository They prominently used Anthropic's Claude AI models (spending under $3,000 in API tokens) to help write, debug, and port the binary exploits faster, showcasing how offensive AI capabilities accelerate vulnerability research.

framing: assertive · carried by 1 article(s) · first seen 2026-09-18

🔮 Three Indian-origin cybersecurity researchers, Harsh Jaiswal, Mohan Pedhapati and Rahul Maini, demonstrated how Anthropic's Claude AI could be used to exploit vulnerabilities and gain access to OpenAI employee accounts and the company's internal code repository, Wall Street Journal reported.

2026-09-18 · Times of India

Meet Harsh Jaiswal, Mohan Pedhapati and Rahul Maini: 3 Indian-origin researchers who used Claude to breach OpenAI systems, won $6,500 bounty · assertive framing

Claims (17 extracted, 3 hedged)

Three Indian-origin cybersecurity researchers, Harsh Jaiswal, Mohan Pedhapati and Rahul Maini, demonstrated how Anthropic's Claude AI could be used to exploit vulnerabilities and gain access to OpenAI employee accounts and the company's internal code repository, Wall Street Journal reported. uncertain

Journal → demonstrate → accounts

The researchers, who work at cybersecurity startup Hacktron AI, carried out the research in July 2026 while investigating security weaknesses at leading AI companies. asserted

who → work → companies

They eventually chained two separate vulnerabilities to move from OpenAI's public community forum to employee ChatGPT and Codex accounts and then to an internal GitHub repository. asserted

They → chain → repository

The researchers said the entire chain, from their initial discovery to demonstrating access to OpenAI's internal repository, took less than 72 hours. asserted

chain → say → hours

They spent under $3,000 on AI tokens and won a bounty of $6,500 after they disclosed the issues to OpenAI. asserted

they → spend → OpenAI

How did the researchers get into OpenAI's systems? asserted

researchers → get → systems

The attack began at community.openai.com, OpenAI's community and help forum, which is operated using the third-party platform Discourse. asserted

which → begin → platform

Hacktron researchers discovered that specially crafted HEIC/HEIF image files could exploit a vulnerability in the image-processing software used by Discourse. uncertain

files → discover → Discourse

The vulnerability was linked to the `libheif` image-decoding library and could allow remote code execution — essentially giving an attacker the ability to execute commands on the affected server. uncertain

vulnerability → link → server

However, gaining control of the forum server alone did not provide direct access to OpenAI's internal code. asserted

gaining → gain → code

capabilities → demonstrate → research

Then they reported the findings responsibly through Bugcrowd and HackerOne to OpenAI and Discourse. asserted

they → report → OpenAI

OpenAI patched the identity issue shortly after notification and awarded them a $6,500 bug bounty. asserted

OpenAI → patch → bounty

In a statement to Forbes, OpenAI spokesperson Drew Pusateri said the company thanked the researchers “for contacting us and sharing their findings,” and noted that it had resolved the vulnerability. asserted

it → say → vulnerability

No brand name, colleges or companies' Tech commentator Deedy Das pointed out that none of the three researchers had any big college name on their CVs. asserted

none → point → CVs

"Here are the LinkedIns of the 3 Indian guys who hacked OpenAI with Opus 5 in 2 days for <$3000: Rahul Maini, Mohan Pedhapati and Harsh Jaiswal. asserted

who → hack → 3000

You can just do things," Das posted. asserted

Das → do → things