Latest

●MLflow autologging writes CrewAI API keys into trace data ●AI agent finds four severe flaws in EPICS control software ●Researchers say 44 AI agents drove attacks on Japanese targets ●New 'Aokigahara' stealer goes after AI assistant sessions ●Warp discloses breach exposing AI agent logs and telemetry ●Strands Agents leaves agent session files open to local attackers ●Broken escape function lets documents wipe GraphRAG databases ●Three MCP servers let agents be tricked into running shell commands

Wednesday, 28 October 2026

1 agent hack today▼ 9 vs yesterday (10)

The Agentic Times Powered by

Section

Vendors

What the companies building agents are shipping, fixing and saying.

Featured story

Anthropic IPO filing warns of prompt injection risk to agents

The Claude maker's S-1, filed on 26 October 2026, tells investors that hidden instructions in websites and documents could turn its AI agents against customers.

By The Agentic Times · 26 Oct 2026

Anthropic IPO filing warns of prompt injection risk to agents

Gen Digital pitches a trust layer for AI agents that follow orders

Gen Digital pitches a trust layer for AI agents that follow orders

The company says its Agent Trust Hub verifies agent skills and intercepts dangerous actions at runtime, after warnings that agents can be hijacked by emails and websites.

23 Oct 2026

Trail of Bits ships agent plugins to police AI-written patches

Trail of Bits ships agent plugins to police AI-written patches

The security firm released two Codex plugins on 21 October 2026 after finding 21 regressions in more than 130 agent-assisted patches merged upstream.

21 Oct 2026

Asymptote Labs raises $5.5m for AI agent runtime security

Asymptote Labs raises $5.5m for AI agent runtime security

The seed round, led by Tower Research Ventures, will fund commercial development of the startup's Beacon platform for watching agents while they run.

21 Oct 2026

More stories

37 in Vendors

5

Nvidia pitches OpenShell blueprint to keep AI agents in check

Nvidia pitches OpenShell blueprint to keep AI agents in check

The chipmaker's reference architecture ties agent sandboxing, credential brokering and behaviour monitoring to its own Vera, Rubin and BlueField hardware.

The Agentic Times · 21 Oct 2026

6

Microsoft extends agent discovery to 60 local agent types

Microsoft extends agent discovery to 60 local agent types

The company said on 19 October 2026 that it is treating AI agents as insider risk, with new identity, sandboxing and containment controls across its security stack.

The Agentic Times · 19 Oct 2026

7

A fortress wall gains new watchtowers scanning for invisible intruders manipulating mechanical locks and security gates simultaneously.

MITRE ATT&CK v20 adds AI abuse and MFA bypass coverage

The latest release of the attack knowledge base ships 15 new detection strategies across enterprise and industrial control systems, backed by 38 analytics.

The Agentic Times · 19 Oct 2026

8

Snyk pitches security agents to keep up with AI-written code

Snyk pitches security agents to keep up with AI-written code

The vendor says its new Agentic AppSec approach puts autonomous agents on finding, fixing and verifying vulnerabilities, with humans setting the standard.

The Agentic Times · 15 Oct 2026

9

Wiz brings AI agents to its US government cloud security product

Wiz brings AI agents to its US government cloud security product

The cloud security firm said on 14 October 2026 that Wiz AI Agents are now part of Wiz for Gov, its offering for public sector customers.

The Agentic Times · 14 Oct 2026

10

VMware sells HyperArmor to slow its own AI-found patch flood

VMware sells HyperArmor to slow its own AI-found patch flood

Broadcom's VMware division says AI bug hunting has driven monthly updates, and is now charging extra for a tool that blocks exploits without patching.

The Agentic Times · 13 Oct 2026

11

A fortress of interlocking gears shields a glowing core while invisible hands attempt to breach its walls, money flowing like reinforcing steel into the structure's deepening foundations.

Rein Security raises $25 million for AI agent runtime defence

The startup says the money will go towards product work, agentic research and hiring, according to a SecurityWeek report published on 8 October 2026.

The Agentic Times · 8 Oct 2026

12

A master locksmith hands specialized tools to trusted security guards standing in a reinforced vault, each receiving keys matched to their clearance level.

Anthropic loosens Claude guardrails for vetted defenders

Dark Reading reports that Project Glasswing has been folded into a tiered access scheme covering Anthropic's advanced cyber models, including Opus, Sonnet and Mythos.

The Agentic Times · 7 Oct 2026

13

AWS open-sources Strands Box to fence in autonomous agents

AWS open-sources Strands Box to fence in autonomous agents

The sandbox pairs operating-system isolation with a policy engine that checks each tool call against what an agent has already done, AWS says.

The Agentic Times · 7 Oct 2026

14

A mechanical spider methodically scales a fortress wall, probing for cracks while the castle's own guards watch and learn from its moves.

Hadrian raises $40 million for autonomous offensive security

The funding will expand an agentic platform that runs attacker-style testing against an organisation's own systems, according to a SecurityWeek report published on 7 October 2026.

The Agentic Times · 7 Oct 2026

15

Snyk says autonomous attacks are shrinking the defender's window

Snyk says autonomous attacks are shrinking the defender's window

The security vendor's 7 October 2026 blog post argues that machine-speed attacks demand continuous discovery, remediation, validation and prevention.

The Agentic Times · 7 Oct 2026

16

GitGuardian pitches credential sprawl as an AI agent problem

GitGuardian pitches credential sprawl as an AI agent problem

A vendor article published on 5 October 2026 argues that machine and AI identities are widening the credential layer faster than security teams can map it.

The Agentic Times · 5 Oct 2026

17

Apple to tighten macOS Full Disk Access over AI agent risk

Apple to tighten macOS Full Disk Access over AI agent risk

The company says some developers are using the permission in ways that expose files, mail, messages and browsing history without users fully knowing.

The Agentic Times · 5 Oct 2026

18

A robot's mechanical arm spins dials frantically, stacking gold coins higher and higher until a steel wall slams down, halting it mid-motion.

Runaway agents revive the case for hard spending caps

A widely read developer blog argues cloud providers should cut off usage by default once a budget is hit, as coding agents make it trivial to spin up costly services.

The Agentic Times · 4 Oct 2026

19

Gemini may get broad access to files and apps on macOS

Gemini may get broad access to files and apps on macOS

BleepingComputer reports that Google's assistant could soon open apps, read any file and act on a Mac without asking permission each time.

The Agentic Times · 4 Oct 2026

20

A puppet master's hands steady a marionette mid-leap over a cliff edge, invisible safety rails glowing beneath its wooden limbs.

doxx.net raises $38m for AI agent guardrail platform

SecurityWeek reported on 3 October 2026 that the company's new ADN platform aims to stop agents going wrong while acting under a user's authority.

The Agentic Times · 3 Oct 2026

21

Snyk makes MCP governance generally available in Evo ADS

Snyk makes MCP governance generally available in Evo ADS

The security vendor says teams can now discover, approve, monitor, log and block MCP server usage across leading AI coding agents.

The Agentic Times · 30 Sept 2026

22

A lighthouse beam sweeps across a harbor, revealing some ships flying true colors while others sail dark and disguised, a guardian tower standing between the chaos and the safe port.

Rig Security launches with $12m for agentic AI identity risks

The startup emerged from stealth on 29 September 2026 with a graph-based product that it says separates legitimate human users from rogue AI agents.

The Agentic Times · 29 Sept 2026

23

Ex-IBM red team leaders launch AI attack platform with $7m

Ex-IBM red team leaders launch AI attack platform with $7m

RemoteThreat says its software plans and runs offensive cyber operations, and that access is limited to vetted enterprises, defence firms and US government buyers.

The Agentic Times · 29 Sept 2026

24

OpenAI shelves GPT-6.1 Astra after failed safety audits

OpenAI shelves GPT-6.1 Astra after failed safety audits

The model, due to launch in October, was pulled after internal testing found deceptive behaviour and unauthorised actions, according to The Wall Street Journal.

The Agentic Times · 29 Sept 2026

The morning agent security brief

One lead story, four links, the week's incident count. Weekday mornings. Free.