Search: “prompt-injection”

10 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll AI safety & security 26 Exploit / PoC 10 Vulnerability 8 Threat actor 5 Malware 2 Model release 2 AI industry 1 Phishing & fraud 1 Research 1 Industry 1 Tools 1 AI tools & infra 1

SeverityAll critical 5 high 6 medium 22 low 5 info 21

Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents

The Hacker NewsJul 22, 14:13 UTC · Jul 22, 2026Exploit / PoC1

45

Webmail CSS Attacks Expose a New Risk for AI

Security AffairsAug 9, 08:01 UTC · Aug 9, 2026Exploit / PoC

45

Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers

The Hacker NewsAug 8, 08:54 UTC · Aug 8, 2026Exploit / PoC in the wild

60

New CSS Attacks Can Break Webmail Defenses to Steal Passwords and Tokens

The Hacker NewsAug 8, 08:03 UTC · Aug 8, 2026Exploit / PoC

45

Google Deletes 3 ADK AI Workflows After Malicious GitHub Issue Could Trigger Privileged Agent

The Hacker NewsAug 4, 11:16 UTC · Aug 4, 2026Exploit / PoC in the wild

60

AWS Kiro Flaw Let a Poisoned Web Page Rewrite Its Config and Run Code

The Hacker NewsJul 24, 04:46 UTC · Jul 24, 2026Exploit / PoC in the wildCVE-2026-10591

60

New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands

The Hacker NewsJul 15, 00:00 UTC · Jul 15, 2026Exploit / PoC CVE-2025-327111

50

ShadowLeak: Radware uncovers zero

Security AffairsSep 18, 23:29 UTC · Sep 18, 2025Exploit / PoC

45

Cursor’s AI coding agent morphed ‘into local shell’ with one

CyberScoopAug 1, 19:51 UTC · Aug 1, 2025Exploit / PoC in the wildCVE-2025-54135

60

Invisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.

Ars Technica · SecurityOct 15, 00:00 UTC · Oct 15, 2024Exploit / PoC1

45