GoKawiil - Tech News

1.

Grok exfiltrates user data when malicious instructions are encrypted (arstechnica.com)

2026-08-20 | tags: grok, microsoft 365 copilot, prompt injection

2.

'CoSnitch' Attack Tricked Copilot into Mapping Out Architecture (darkreading.com)

2026-08-18 | by Alexander Culafi | tags: copilot, varonis, cosnitch

3.

Dude Reportedly Hides Prompt Injections in Legal Filing, Just in Case Judge Is Really That Lazy (gizmodo.com)

2026-08-15 | tags: prompt injections, legal filing, dude

4.

Suspecting court of using AI, man injected prompts in filings to try to win case (news.ycombinator.com)

2026-08-15 | tags: prompt injection, court filings, spader jr

5.

Suspecting court of using AI, man injected prompts in filings to try to win case (arstechnica.com)

2026-08-14 | tags: prompt injection, court filings, spader

6.

Person Hides Prompt Injection In Legal Filing Telling AI To Side With Them (slashdot.org)

2026-08-14 | tags: prompt injection, legal filing, oscar wilde

7.

Plaintiff busted trying to use AI prompt injection to win court case, hides text instruction in filing — demands AI model reviewing the text should side with him, rumbled because of strange white spaces in text (tomshardware.com)

2026-08-14 | by Jowi Morales | tags: ai prompt injection, matthew elliot, ny bariatric group

8.

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

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

9.

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

10.

‘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

11.

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

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

12.

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

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

13.

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

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

14.

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

15.

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

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

16.

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

17.

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

18.

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

19.

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

20.

Malicious Notifications Could Trick Google Gemini Users (darkreading.com)

2026-06-03 | by Alexander Culafi | get Google Gemini Security Kit → | tags: google gemini, voice assistant, prompt injection

21.

Hackers duped Meta AI support chatbot to steal celebrity Instagram accounts (arstechnica.com)

2026-06-01 | get AI Security Monitoring Tool → | tags: meta ai, instagram, vpn

22.

Anthropic’s browser agent got hijacked 31.5% of the time before safeguards engaged (venturebeat.com)

2026-06-01 | get AI Security Browser Extension → | tags: anthropic, prompt injection, frontier labs

23.

ChatGPT for Google Sheets exfiltrates workbooks (news.ycombinator.com)

2026-05-31 | get AI-powered Google Sheets Add-on → | tags: chatgpt, google sheets, openai

24.

ChatGPT for Google Sheets Exfiltrates Workbooks (news.ycombinator.com)

2026-05-31 | get ChatGPT for Google Sheets Add-on → | tags: openai, chatgpt, google sheets

25.

Undisclosed addition in jqwik instructed AI coding agents to delete app output (news.ycombinator.com)

2026-05-29 | tags: jqwik, junit 5, java

26.

Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code (arstechnica.com)

2026-05-28 | get Secure Coding Practice Book → | tags: jqwik, java, prompt injection

27.

Microsoft Copilot Cowork Exfiltrates Files (news.ycombinator.com)

2026-05-25 | get Microsoft 365 Copilot → | tags: microsoft, copilot, microsoft 365

28.

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)

2026-05-17 | by Mark Tyson | get AI Prompt Injection Detection Tool → | tags: linkedin, prompt injection, tmuxvim

29.

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)

2026-05-17 | by Mark Tyson | get AI Prompt Injection Defense Tool → | tags: linkedin, prompt injection, tmuxvim

30.

Google Studies Prompt Injection Attacks Against AI Agents Browsing the Web (slashdot.org)

2026-04-26 | by Posted | get AI Safety and Security Book → | tags: prompt injection, google ai, ai agents