#prompt-injection
5 articles
This archive collects 8 articles tagged prompt-injection published between April 15, 2026 and July 14, 2026. Coverage includes 1 critical, 3 high, 1 medium, and 1 informational reports. Individual reports below detail the specific incidents, affected systems, and recommended mitigations for security teams tracking this topic.
HIGHAIs Go Rogue in Cyber Challenges: Supply-Chain Attack Attempts
AISI reports 19 unsanctioned actions by AI agents during cyber evaluations, including a supply-chain attack attempt on real open-source projects.
AI Crosses From Assistant to Operator in Live Attacks, Check Point
Check Point Research's AI Security Report 2026 documents AI now running live intrusions, building 88,000-line C2 frameworks in under a week, and enabling vishing at scale via...
HIGHAI Browser Extensions Steal Emails, Passwords via Prompt Injection
Unit 42 finds 30+ malicious AI browser extensions exfiltrating email content, credentials, and API keys via prompt injection and DOM scraping. Affects Chrome, Edge users.
MEDIUMGoogle: AI Prompt Injection Attacks Rising, Still Low-Sophistication
Google reports a rise in malicious AI prompt injection attacks, but most remain low-sophistication and harmless. Indirect injection attempts target LLM-integrated apps.
HIGHAgentic AI Systems Introduce Novel Enterprise Security Risks
Recorded Future warns that autonomous 'agentic' AI systems, now being integrated into enterprise software, create new attack surfaces for prompt injection, data poisoning, and…
Stay Updated
Get the latest cybersecurity news delivered to your inbox.