Curated security research, vulnerabilities, advisories and tools for practitioners.

#autonomous-agents

Security coverage tagged autonomous-agents.

1.

Introducing Autonomous Exposure Management: Offensive Security at Enterprise Scale

blog | 2026-09-24 12:00 | xbow.com | Original ↗ | .md | #ai-security | #attack-surface | #exposure-management

2.

Can AI invent new attack techniques? New research from James Kettle and PortSwigger Research

blog | 2026-08-12 09:04 | portswigger.net | Original ↗ | .md | #ai-security | #black-hat | #web-security

3.

Engineering the Impossible: Adding Safety to Autonomous Agents

blog | 2026-08-12 12:00 | xbow.com | Original ↗ | .md | #ai-safety | #sandboxing | #offensive-security

4.

Can AI do novel security research? Meet the HTTP Terminator

research | 2026-08-06 14:59 | portswigger.net | Original ↗ | .md | #ai-security | #agentic-ai | #vulnerability-research

5.

Grok 4.5 Is Powerful. The System Around It Makes It Safe.

blog | 2026-07-31 12:00 | xbow.com | Original ↗ | .md | #ai-security | #pentesting | #agentic-ai

6.

Why Uniform Governance Fails with Enterprise AI Agents (And How to Fix It)

blog | 2026-06-24 15:58 | jfrog.com | Original ↗ | .md | #ai-security | #supply-chain | #devsecops

7.

How JFrog and NanoClaw are Bringing Software Supply Chain Security to the Age of Autonomous AI

blog | 2026-06-24 13:15 | jfrog.com | Original ↗ | .md | #ai-security | #supply-chain | #mcp

8.

The Search for AGI through Security: Introducing the World's First AI-Based Novel Attack Vector Researcher

blog | 2026-04-10 09:12 | pwn.ai | Original ↗ | .md | #ai-security | #vulnerability-research | #offensive-security

9.

ImageMagick: From Arbitrary File Read to File Write In Every Policy

blog | 2026-03-30 07:06 | pwn.ai | Original ↗ | .md | #ai-security | #rce | #zero-day

10.

AI Pentesting: Minimum Safety Requirements for Security Testing

blog | 2026-02-03 00:00 | aikido.dev | Original ↗ | .md | #ai-security | #appsec | #security-testing

11.

The Agents Behind Hackerone Agentic PTaaS: Proven, Scalable, and Benchmarked

blog | 2026-01-26 14:07 | hackerone.com | Original ↗ | .md | #ai-security | #pentesting | #agentic-ai

12.

CVE-2025-54322 (ZERODAY) - Unauthenticated Root RCE affecting ~70,000+ Hosts

vulnerability | Critical | 2025-12-26 16:25 | CVE-2025-54322 | pwn.ai | Original ↗ | .md | #ai-security | #rce | #zero-day

13.

Task Injection – Exploiting agency of autonomous AI agents

blog | 2025-12-11 00:00 | bughunters.google.com | Original ↗ | .md | #ai-security | #prompt-injection | #ai-agents