Google joins the ‘Oops, our agents hacked someone’ club after partner’s internet access error
What's happening
A team of three independent security researchers used Anthropic's Claude (Opus 4.8 and 5) to compromise OpenAI employee accounts and access OpenAI's GitHub "Monorepo," which reportedly contains "OpenAI's algorithmic secrets." The researchers said the attack took less than 72 hours and that Claude helped them reach an OpenAI employee account and sensitive GitHub data. The researchers reported the flaws after taking over accounts and gaining repository access.
Why it's trending
This is rising because multiple outlets and researchers are reporting an agentic exploit that used Claude to breach high-profile AI company infrastructure within days.
SignalHolding at its usual pace, confirmed across 3 independent source types.
Momentum
Score per dayStory volume
Stories per dayAngles you could write
If Claude can turn into a 72-hour locksmith against OpenAI's Monorepo, maybe the real risk isn't 'AI gone rogue' but whoever lets the AI log into their systems for them.
+2 more angles for this topic with an account — all it takes is your email.
Original sources22
- Don’t be fooled by this summer of AI hype
It’s been a busy few months for AI hype. At the end of April, Anthropic claimed that its model Claude Mythos is better at finding software vulnerabilities than most security experts. Then we had the OpenAI–Hugging Face hacking incident, after which Anthropic (proudly) and Meta (reluctantly) disclosed similar incidents involving their models. This was followed…
MIT Tech ReviewSep 22 - OpenAI and Anthropic oversold AI security breaches to pressure feds into protecting turf: insidersr/OpenAISep 21
- OpenAI and Anthropic oversold AI security breachesHackerNewsSep 19
+19 more sources for this topic
Create an account to follow the full coverage in the live radar.
More rising in AI & Tech
- An Anthropic AI model sent a false homicide tip to Philadelphia policeClimbing1.8Climbing1.8 momentum
- Sam Altman says ‘some bad things’ will happen, but AI is totally worth itSteady1.3Steady1.3 momentum
- Satya Nadella says we should assume all AI models are ‘compromised’Climbing3.1Climbing3.1 momentum
- AI company moves to defend critical infrastructure and open-source projects from AISteady1.1Steady1.1 momentum
- CA tech CEO arrested for smuggling $300 million in restricted AI chips into China (Video)Steady0.7Steady0.7 momentum
- ‘Pure insanity’: Mathematicians will need years to make sense of OpenAI’s latest dropClimbing1.8Climbing1.8 momentum