prompt injection

4 min read

• AI
• AI agents
• artificial intelligence (AI)
• Cybersecurity
• incident response
• large language models
• Microsoft
• open source
• prompt injection
• red team
• vulnerability reporting

Meet Rampart and Clarity, Microsoft’s new red team combo AI agents

Cyber Scoop May 20, 2026

Meet Rampart and Clarity, Microsoft’s new red team combo...

Read More

3 min read

• Agentic AI
• AI
• artificial intelligence (AI)
• Cybersecurity
• Cybersecurity and Infrastructure Security Agency (CISA)
• Government
• identity management
• nsa
• prompt injection
• Technology

US government, allies publish guidance on how to safely deploy AI agents

Cyber Scoop May 1, 2026

US government, allies publish guidance on how to safely...

Read More

5 min read

• AI
• artificial intelligence (AI)
• Grafana
• Noma Security
• prompt injection
• Threats

‘GrafanaGhost’ bypasses Grafana’s AI defenses without leaving a trace

Cyber Scoop April 7, 2026

‘GrafanaGhost’ bypasses Grafana’s AI defenses without leaving a trace...

Read More

3 min read

• Agentic AI
• AI
• artificial intelligence (AI)
• Cybersecurity
• large language models
• prompt injection
• Research

Researchers discover suite of agentic AI browser vulnerabilities

Cyber Scoop March 3, 2026

Researchers discover suite of agentic AI browser vulnerabilities |...

Read More

3 min read

• Agentic AI
• AI
• artificial intelligence (AI)
• mergers and acquisitions
• model context protocol (MCP)
• Money
• prompt injection
• Proofpoint

Proofpoint acquires Acuvity to tackle the security risks of agentic AI

Cyber Scoop February 12, 2026

Proofpoint acquires Acuvity to tackle the security risks of...

Read More

3 min read

• AI
• Cybersecurity
• prompt injection
• Research
• servicenow
• Threats
• vulnerability

ServiceNow patches critical AI platform flaw that could allow user impersonation

Cyber Scoop January 13, 2026

ServiceNow patches critical AI platform flaw that could allow...

Read More

4 min read

• AI
• AI browser
• artificial intelligence (AI)
• ChatGPT
• Cybersecurity
• OpenAI
• prompt injection
• Research

OpenAI says prompt injection may never be ‘solved’ for browser agents like Atlas

Cyber Scoop December 30, 2025

OpenAI says prompt injection may never be ‘solved’ for...

Read More

5 min read

• AI
• artificial intelligence (AI)
• Cybersecurity
• Government
• guidance
• large language models
• prompt injection
• Research
• UK

UK cyber agency warns LLMs will always be vulnerable to prompt injection

Cyber Scoop December 8, 2025

UK cyber agency warns LLMs will always be vulnerable...

Read More

4 min read

• AI
• AI agents
• ai coding
• Anthropic
• artificial intelligence (AI)
• Cybersecurity
• Google
• OpenAI
• prompt injection
• software development
• software security
• Technology

More evidence your AI agents can be turned against you

Cyber Scoop December 5, 2025

More evidence your AI agents can be turned against...

Read More

6 min read

• AI
• AI safety
• AI security
• Anthropic
• artificial intelligence (AI)
• Claude
• Cybersecurity
• disinformation
• prompt injection
• Research

Anthropic touts safety, security improvements in Claude Sonnet 4.5

Cyber Scoop September 30, 2025

Anthropic touts safety, security improvements in Claude Sonnet 4.5...

Read More