EUVD-2026-46578

Vulnerability in Oracle Autonomous Health Framework component: Developer triaging platform. Supported versions that are affected are 26.0.0, 26.1.0 and 26.2.0. Difficult to exploit vulnerability allows high privileged attacker with logon to the infrastructure where Oracle Autonomous Health...

CVE-2026-60172

Vulnerability in Oracle Autonomous Health Framework component: Developer triaging platform. Supported versions that are affected are 26.0.0, 26.1.0 and 26.2.0. Difficult to exploit vulnerability allows high privileged attacker with logon to the infrastructure where Oracle Autonomous Health...

World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent

In an ironic twist, open-source artificial intelligence AI platform Hugging Face revealed that it was the victim of a hack perpetrated by an autonomous AI agent system. The company said it detected and responded to the incident targeting its production infrastructure earlier last week. "We...

Xalgorix Autonomous AI Pentesting Agent 4.5.67

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

The Race to Field Military Autonomy Is On, Can Trusted Information Infrastructure Keep Pace?

Military forces are under increasing pressure to field autonomous capabilities faster than ever before. Across the U.S., UK, and NATO, new investment, evolving defense strategies, and accelerated acquisition pathways are transforming how capability is delivered, rewarding programs that can move...

DEBIAN-CVE-2026-14461

mtr is vulnerable to Out-of-bound read vulnerability in ipinfolookup function. An attacker who can influence the TXT response used for AS lookups can trigger this bug by returning a DNS response that is larger than 512 bytes and uses a crafted compression pointer in the answer NAME...

CVE-2026-14461 Out-of-bound read in mtr

mtr is vulnerable to Out-of-bound read vulnerability in ipinfolookup function. An attacker who can influence the TXT response used for AS lookups can trigger this bug by returning a DNS response that is larger than 512 bytes and uses a crafted compression pointer in the answer NAME...

PT-2026-57024

Name of the Vulnerable Software and Affected Versions gobgp affected versions not specified Description GoBGP fails to properly handle BGP UPDATE messages containing a zero-length AS PATH attribute. When a configured confederation eBGP peer sends a malformed UPDATE with a syntactically valid AS...

Guardian Agents: The Next Layer of Identity Governance

AI agents are moving through enterprise environments, inheriting permissions, traversing systems, and executing decisions at machine speed with minimal oversight. The identity infrastructure built to govern human access wasn't designed for autonomous actors, and the gap between what enterprises a...

OffSploit

OffSploit: Autonomous Exploit Adaptation & C2 Framework !Py...

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross. Within this broader red-line scenario, autonomous penetration represents a core enabling capability and...

Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models

University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-weight large language model to reason its way through a network, generate tailored attack strategies for each target it encounters, and replicate itself, all without...

pentestai

PentestAI Autonomous penetration testing framework for intent...

PT-2026-47172

An autonomous AI security agent just found 21 zero-days in FFmpeg for $1,000. Some were 23 years old. All came with working PoCs. CVE-2026-39210 through 39218 assigned. 12 more fixed, not yet numbered. This is what commodity AI vulnerability research https://t.co/zpeiwGSVQh https://t.co/ad6T1JxzD...

PT-2026-47173

$1,000 of compute found 21 zero-days in FFmpeg. An autonomous agent called depthfirst scanned roughly 1.5 million lines of C, then wrote a reproducible proof-of-concept for every bug it reported. The shift is that second half. Not a list of suspicious lines for a human to chase, but 21 crashing...

Closing the Sim-To-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR

Leading commercial endpoint detection and response EDR products have shifted from operator-configured rule sets to multi-component systems where autonomous AI components operate alongside, and increasingly in place of, operator-deployed policies. Autonomous defense agents using commercial EDR as...

CVE-2026-1718

IBM Db2 11.5.0 through 11.5.9, and 12.1.0 through 12.1.4 is vulnerable to a denial of service with a specially crafted query when autonomous transactions are enabled...

CVE-2026-49943

CZ.NIC BIRD Internet Routing Daemon (up to version 2.19.0) is affected by a stack-based buffer overflow in the BGP AS_PATH mask matching implementation (nest/a-path.c). The as_path_match() routine uses a fixed-size stack capable of 2048 + 1 pm_pos entries, while parse_path() expands AS_PATH segme...

snyk-agentic-appsec-poc

Snyk Agentic AppSec POC Proof of concept demonstrating autono...

SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents

Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-world workflows, they also introduce security risks that are difficult to capture with existing evaluations. Current agent...