GoKawiil - Tech News

1.

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

2.

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

3.

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

4.

There’s no rogue McDonald’s AI bot, but ‘prompt injection’ is still a risk for companies (feeds.feedburner.com)

2026-04-24 | get AI Prompt Injection Defense Kit → | tags: mcdonalds, prompt injection, ai bots

5.

No, McDonald’s AI bot didn’t go rogue, but ‘prompt injection’ is still a risk for companies (feeds.feedburner.com)

2026-04-24 | get AI Prompt Injection Security Kit → | tags: mcdonalds, ai bot, prompt injection

6.

How indirect prompt injection attacks on AI work - and 6 ways to shut them down (zdnet.com)

2026-04-24 | by Charlie Osborne | get AI Prompt Security Kit → | tags: large language models, prompt injection, ai chatbots

7.

Google Fixes Critical RCE Flaw in AI-Based 'Antigravity' Tool (darkreading.com)

2026-04-21 | by Elizabeth Montalbano | get AI-Powered Gravity Simulator → | tags: google, antigravity, prompt injection

8.

Three AI coding agents leaked secrets through a single prompt injection. One vendor's system card predicted it (venturebeat.com)

2026-04-21 | get AI Security Monitoring Kit → | tags: anthropic, github copilot, google gemini

9.

Google Fixes Critical RCE Flaw in AI-Based Antigravity Tool (darkreading.com)

2026-04-21 | by Elizabeth Montalbano | get AI Antigravity Device Kit → | tags: google, antigravity, pillar security

10.

Microsoft patched a Copilot Studio prompt injection. The data exfiltrated anyway (venturebeat.com)

2026-04-15 | get Microsoft Surface Laptop 4 → | tags: microsoft, copilot studio, prompt injection

11.

Microsoft patched a Copilot Studio prompt injection. The data exfiltrated anyway. (venturebeat.com)

2026-04-15 | get Cybersecurity Privacy USB → | tags: microsoft, copilot studio, prompt injection

12.

Microsoft, Salesforce Patch AI Agent Data Leak Flaws (darkreading.com)

2026-04-15 | get AI Security Monitoring Kit → | tags: microsoft, salesforce, copilot

13.

Researchers detail how a prompt injection attack bypassed Apple Intelligence protections (9to5mac.com)

2026-04-09 | by Marcus Mendes | get SecureGPT Prompt Security Kit → | tags: apple, prompt injection, on-device model

14.

PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free (news.ycombinator.com)

2026-04-03 | get AI Prompt Security Kit → | tags: pigguard, prompt injection, notinject

15.

"Disregard That" Attacks (news.ycombinator.com)

2026-03-25 | tags: prompt injection, large language model, claude

16.

Anthropic hands Claude Code more control, but keeps it on a leash (techcrunch.com)

2026-03-24 | by Rebecca Bellan | get Claude AI Developer Kit → | tags: anthropic, claude, ai safeguards

17.

Snowflake AI Escapes Sandbox and Executes Malware (news.ycombinator.com)

2026-03-18 | get Cybersecurity Threat Detection Kit → | tags: snowflake, cortex code, sandbox

18.

'Claudy Day’ Trio of Flaws Exposes Claude Users to Data Theft (darkreading.com)

2026-03-18 | get Data Security USB Drive → | tags: claude, prompt injection, google

19.

Agent Skills – Open Security Database (news.ycombinator.com)

2026-03-16 | get Cybersecurity Open Database Tool → | tags: agent skills, security index, github

20.

The biggest AI threats come from within - 12 ways to defend your organization (zdnet.com)

2026-03-05 | by Webb Wright | get Artificial Intelligence → | tags: ai threats, cybersecurity, ey report

21.

These 4 critical AI vulnerabilities are being exploited faster than defenders can respond (zdnet.com)

2026-02-12 | by Dan Patterson | get Artificial Intelligence → | tags: attacks, injection, prompt

22.

Is a secure AI assistant possible? (technologyreview.com)

2026-02-11 | by Grace Huckins | get Artificial Intelligence Assistant → | tags: injection, prompt, prompt injection

23.

Rules fail at the prompt, succeed at the boundary (technologyreview.com)

2026-01-28 | by Jessica Hammond | get Smartphone → | tags: agent, control, model

24.

Notion AI: Unpatched data exfiltration (news.ycombinator.com)

2026-01-07 | get Notion AI → | tags: document, injection, notion

25.

OpenAI says AI browsers may always be vulnerable to prompt injection attacks (techcrunch.com)

2025-12-22 | by Rebecca Bellan | get Google Chrome → | tags: agent, atlas, openai