79% vs 51%: independent neobanks lag on app security. Read the report

Tag

#agentic ai

6 articles

ARTEX went from a July GitHub release to bank breaches, a ConnectWise supply-chain compromise and a 200-target espionage campaign. What its agents do, what they leave in logs, and what to close first.

Security

Does AI Security Testing Hallucinate? LLM Guesses vs. Proof-of-Exploit

Language models hallucinate by default, and security findings are no exception. See why, and the ...

Nov 09, 2026

Security

Can an AI Agent Prove SAST Findings at Runtime?

Static analysis flags possible bugs but cannot prove them. Runtime validation proved a Langflow a...

Sep 23, 2026

Security

Post-Mortem: Why Autonomous AI Agents Escape Scope and How to Contain Them

A technical post-mortem on an AI agent that wandered outside its testing scope during an authoriz...

Sep 18, 2026

More tagged #agentic ai

Autonomous Penetration Testing vs Traditional Pentesting

Autonomous penetration testing vs manual pentests and PTaaS: compare agentic AI runtime proof, human-led business logic testing, and hybrid workflows.

Sep 08, 2026

AI Can Run the Attack. Can You Trust the Result?

AI can produce a convincing exploit story in seconds. Runtime proof, negative controls, and human review determine whether that story becomes a finding a security team can trust.

Aug 06, 2026