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…
-
GitLost Showed GitHub Agentic Workflows Could Leak Private Repositories From a Public Issue
GitLost showed that GitHub Agentic Workflows could be steered from a public GitHub issue into reading a private repository and…
-
Prompt Injection Became Serious Enough for ICML to Police in Peer Review
Prompt injection is an LLM attack that makes a model follow untrusted instructions hidden in user input or external content,…
-
Firefox Zero-Day: Mozilla Says Claude Mythos Found 271 Bugs
Mozilla said this week that its Firefox zero-day hardening work with an early version of Claude Mythos Preview helped identify…
-
125 Words, No Account Cues: AI Identifies Writer From Style
Anthropic’s Claude Opus 4.7 reportedly identified journalist Kelsey Piper from 125 words of unpublished text, and the details of her…
-
SMS Blaster Bust Exposes the Limits of SMS Trust
Toronto police say they seized several devices they describe as an SMS blaster, a fake-cell-tower tool used to send fraudulent…
