Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
1.
7,000 Langflow servers are under attack. LangGraph and LangChain have the same holes (venturebeat.com)
2.
Copilot 'SearchLeak' Attack Allows 1-Click Data Theft (darkreading.com)
3.
CISA warns of cyberattacks targeting fuel tank monitoring systems (bleepingcomputer.com)
4.
Malicious Notifications Could Trick Google Gemini Users (darkreading.com)
5.
Hackers duped Meta AI support chatbot to steal celebrity Instagram accounts (arstechnica.com)
6.
Anthropic’s browser agent got hijacked 31.5% of the time before safeguards engaged (venturebeat.com)
7.
ChatGPT for Google Sheets exfiltrates workbooks (news.ycombinator.com)
8.
ChatGPT for Google Sheets Exfiltrates Workbooks (news.ycombinator.com)
9.
Undisclosed addition in jqwik instructed AI coding agents to delete app output (news.ycombinator.com)
10.
Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code (arstechnica.com)
11.
Microsoft Copilot Cowork Exfiltrates Files (news.ycombinator.com)
12.
Ghost CMS SQL injection flaw exploited in large-scale ClickFix campaign (bleepingcomputer.com)
13.
Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems (news.ycombinator.com)
14.
Drupal: Critical SQL injection flaw now targeted in attacks (bleepingcomputer.com)
15.
Patch Now: Critical Flaw in OT Robot OS Gives Attackers Control (darkreading.com)
16.
LinkedIn user hides AI prompt injection in bio to force recruitment spam to be sent in Olde English prose — bots also manipulated to address user as ‘My Lord’ (tomshardware.com)
17.
LinkedIn user hides AI prompt injection in bio to force recruitment spam to be sent in Olde English prose — bots also also manipulated to address user as ‘My Lord’ (tomshardware.com)
18.
SAP fixes critical vulnerabilities in Commerce Cloud and S/4HANA (bleepingcomputer.com)
19.
Slimline Commodore 64C Ultimate Edition computers go up for pre-order — firm reintroduces the C64’s sleeker 1986-1994 styling across the range (tomshardware.com)
20.
Hackers are exploiting a critical LiteLLM pre-auth SQLi flaw (bleepingcomputer.com)
21.
Google Studies Prompt Injection Attacks Against AI Agents Browsing the Web (slashdot.org)
22.
There’s no rogue McDonald’s AI bot, but ‘prompt injection’ is still a risk for companies (feeds.feedburner.com)
23.
No, McDonald’s AI bot didn’t go rogue, but ‘prompt injection’ is still a risk for companies (feeds.feedburner.com)
24.
How indirect prompt injection attacks on AI work - and 6 ways to shut them down (zdnet.com)
25.
Google Fixes Critical RCE Flaw in AI-Based 'Antigravity' Tool (darkreading.com)
26.
Three AI coding agents leaked secrets through a single prompt injection. One vendor's system card predicted it (venturebeat.com)
27.
Google Fixes Critical RCE Flaw in AI-Based Antigravity Tool (darkreading.com)
28.
Microsoft patched a Copilot Studio prompt injection. The data exfiltrated anyway (venturebeat.com)
29.
Microsoft patched a Copilot Studio prompt injection. The data exfiltrated anyway. (venturebeat.com)
30.
Microsoft, Salesforce Patch AI Agent Data Leak Flaws (darkreading.com)
Today's top topics: android authority polymarket chatgpt apple anthropic fake bets sony ai chatbots iphone ifixit
View all today's topics →