GoKawiil - Tech News

31.

AMD borrows $4.75 billion for 'general corporate purposes' — company gives no insight into how it plans to spend cash injection (tomshardware.com)

2026-08-14 | by Anton Shilov | tags: amd, intel, securities

32.

No Perfect Fix for AI Browser Prompt Injection Flaws (darkreading.com)

2026-08-05 | tags: according new, ai browsers, attacks

33.

Atlassian Rovo Exfiltrates Data, Bypassing Controls (news.ycombinator.com)

2026-08-05 | tags: atlassian, attack, confluence

34.

Gemini Spark now has Chrome web-browsing capabilities (engadget.com)

2026-08-03 | by Lawrence Bonk | tags: google, chrome, google assistant

35.

Gemini Spark now works with Chrome, because giving your accounts to AI is a good idea (androidauthority.com)

2026-07-31 | tags: gemini spark, google chrome, google ai pro

36.

After the Break-In: What Attackers Do Once They're Already Inside (bleepingcomputer.com)

2026-07-30 | tags: huntress, microsoft sql server, sql injection

37.

‘Fighting fire with fire’: Job candidates are sneaking AI prompt injections into their applications (feeds.feedburner.com)

2026-07-29 | tags: ai prompt injections, hiring manager, resume

38.

Document-borne AI worms can self-propagate through Copilot for Word (news.ycombinator.com)

2026-07-29 | tags: copilot, microsoft security response center, word

39.

Arista patches VeloCloud Orchestrator zero-day exploited in attacks (bleepingcomputer.com)

2026-07-27 | tags: arista, velocloud orchestrator, cve-2026-16812

40.

ANSI escape injection in MCP servers: Hidden from humans, visible to AI (news.ycombinator.com)

2026-07-21 | tags: ansi escape sequences, mcp servers, kubectl

41.

Prompt Injection Attacks Are Thwarting AI Hacking Agents (wired.com)

2026-07-18 | by Dan Goodin | tags: prompt injection, large language models, tracebit

42.

Show HN: ReasonGate- An explainable gate that blocks LLM prompt injection (news.ycombinator.com)

2026-07-16 | tags: reasongate, llm, prompt injection

43.

CVE-2026-25089: FortiSandbox unauthenticated command injection added to CISA KEV (news.ycombinator.com)

2026-07-16 | tags: fortinet, fortisandbox, cve-2026-25089

44.

Now, defenders are embracing the prompt injection, too (arstechnica.com)

2026-07-13 | tags: agents, commands, context

45.

'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets (bleepingcomputer.com)

2026-07-11 | tags: code, image, researchers

46.

Prismata: Confining cross-site prompt injection in web agents (news.ycombinator.com)

2026-07-10 | tags: comments

47.

Factories Are Just Rooms (news.ycombinator.com)

2026-07-03 | get Smart Factory Automation Kit → | tags: ai clock, shenzhen, injection moulding

48.

Opera rolls out Paste Protect feature to fight ClickFix attacks (bleepingcomputer.com)

2026-07-02 | get Opera Browser Security Extension → | tags: opera, paste protect, clickfix

49.

Claude helped uncover a ticketing flaw able to unlock free VIP festival passes (androidauthority.com)

2026-07-01 | get Ticketing Security Scanner → | tags: anthropic, claude, front gate tickets

50.

AI researchers trick chatbots into sharing how to make cocaine as long as they believe a user is wearing a green shirt — 'CoT Forgery' exploit spurs LLMs to divulge forbidden info by faking trusted chains of thought (tomshardware.com)

2026-07-01 | by Luke James | tags: openai, chatbots, prompt injection

51.

New BioShocking attack manipulates AI browser into data theft (bleepingcomputer.com)

2026-06-30 | get AI Security Browser Extension → | tags: bioshocking, layerx, chatgpt atlas

52.

Prompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers (venturebeat.com)

2026-06-28 | get AI Security Monitoring Kit → | tags: large language models, prompt injection, owasp llm top 10

53.

What happened after 2k people tried to hack my AI assistant (news.ycombinator.com)

2026-06-26 | get AI Security Monitoring Kit → | tags: ai assistant, openclaw, hacker news

54.

Computer use in Gemini 3.5 Flash (news.ycombinator.com)

2026-06-24 | by Mateo Quiros | tags: gemini 3.5 flash, adversarial training, enterprise safeguard systems

55.

Prompt Injection as Role Confusion (news.ycombinator.com)

2026-06-22 | by Charles Ye | get AI Prompt Engineering Guide → | tags: prompt injection, role confusion, large language models

56.

Read this before you vibe-code another app (theverge.com)

2026-06-22 | by Yael Grauer | get Smartphone Screen Cleaning Kit → | tags: sql injection, vibe-code, pocketos

57.

7,000 Langflow servers are under attack. LangGraph and LangChain have the same holes (venturebeat.com)

2026-06-19 | get Cybersecurity Server Protection Kit → | tags: langflow, langgraph, langchain

58.

Copilot 'SearchLeak' Attack Allows 1-Click Data Theft (darkreading.com)

2026-06-15 | get Cybersecurity Data Leak Kit → | tags: copilot, searchleak, ai prompt-injection

59.

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks (techcrunch.com)

2026-06-06 | by Anthony Ha | get AI Prompt Security Kit → | tags: lockdown, lockdown mode, mode

60.

OpenAI rolls out a Lockdown Mode for extra protection against prompt injection attacks (engadget.com)

2026-06-05 | by Igor Bonifacic | get OpenAI Security Badge → | tags: chatgpt, lockdown, lockdown mode