Told Not to Do Anything Destructive, Claude Filed a Fake Murder Tip
On July 18, at about 11:30 at night, Anthropic’s Claude Haiku 4.5 typed a made-up eyewitness account into the Philadelphia…
-
-
OpenAI’s Rogue Agents Ran up a Bill. Wikipedia’s Donors Pay It
The Wikimedia Foundation, the donor-funded nonprofit behind Wikipedia, says agents operated by OpenAI sent millions of automated requests to its…
-
OpenAI Model Accessed Medicare Portal; Australia Told 84 Days Later
An OpenAI model researching Australian public healthcare costs reached areas of the Medicare Statistics Reporting Service that the government says…
-
Alabama Put OpenAI’s Agent Escape Under Subpoena
Alabama Attorney General Steve Marshall opened a consumer-protection investigation and issued OpenAI a subpoena on August 24, 2026, over safeguards…
-
Reasoning Logs Hid 704 Secrets. the Old Envelopes May Still Open
Publicly shared LLM API logs can still expose customer data hidden inside encrypted reasoning blocks, at least unless providers have…
-
Anthropic, OpenAI and Google Reasoning Locks Met Their Own Spare Keys
Researchers reported on August 10, 2026, that they could extract supposedly hidden reasoning traces from Anthropic, OpenAI, and Google API…
-
Claude’s “sensitive Leak” Was a Prompt-injection Exfiltration Path
Claude’s reported “highly sensitive” leak demo showed exfiltration from Claude’s active chat context and tools, not a demonstrated cross-user or…
-
Researchers Used Claude’s Web Fetch to Steal User Profile Data
Claude’s reported “secrets leak” attack demonstrated a real prompt-injection exfiltration path through Claude’s then-allowed web_fetch link-following behavior and access to…
-
One Public Issue Could Make GitHub’s AI Workflows Leak Private Repos
GitLost showed that GitHub Agentic Workflows could be steered from a public GitHub issue into reading a private repository and…
