Lucene search
+L

566 matches found

The Hacker News
The Hacker News
•added 2026/07/31 11:21 a.m.•24 views

Chinese Hacker Commands DeepSeek via Telegram to Launch Autonomous Attacks

Palo Alto Networks' Unit 42 says a Chinese-speaking threat actor used DeepSeek through the open-source Hermes Agent framework to launch attacks autonomously. After an initial Telegram instruction, the agent found internet-facing systems and selected public exploits. The researchers recovered no...

9.8CVSS8.1AI score0.37865EPSS
SaveExploits33
Packet Storm News
Packet Storm News
•added 2026/07/31 12:00 a.m.•17 views

Xalgorix Autonomous AI Pentesting Agent 4.5.124

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...

5.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/07/30 12:00 a.m.•16 views

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

5.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/07/29 12:00 a.m.•20 views

Open Security Benchmark: Towards Autonomous Enterprise Cyber Defense

Enterprises are moving toward autonomous cyber defense: agentic AI that builds situational awareness of an organization's security state and reasons from it to assessments, decisions, and actions. This rests on a holistic view of the enterprise's security state, the continuous, cross-vendor pictu...

5.5AI score
SaveExploits0
GithubExploit
GithubExploit
•added 2026/07/28 2:09 p.m.•76 views

Vulnera

Strix The open-source AI pentesting tool. Autonomous AI h...

6.2AI score
SaveExploits0
Wiz blog
Wiz blog
•added 2026/07/27 2:00 p.m.•18 views

Atlas: Wiz's autonomous AI Agent for vulnerability research, ranked #1 on CyberGym

See how Wiz built Atlas, an autonomous AI system for vulnerability research that validates every finding with a real, working exploit...

5.8AI score
SaveExploits0
EUVD
EUVD
•added 2026/07/22 12:31 a.m.•16 views

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...

6.3CVSS7.1AI score0.00141EPSS
SaveExploits0References2
NVD
NVD
•added 2026/07/21 10:17 p.m.•16 views

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...

6.3CVSS0.00141EPSS
SaveExploits0References1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/07/21 12:00 a.m.•1 views

CVE-2026-60172: Improper Access Control

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...

6.3CVSS5.7AI score0.00141EPSS
SaveExploits0References3
The Hacker News
The Hacker News
•added 2026/07/20 5:27 a.m.•47 views

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...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/07/20 12:00 a.m.•37 views

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...

5.4AI score
SaveExploits0
GithubExploit
GithubExploit
•added 2026/07/18 8:39 a.m.•109 views

deep-pentest-skill

Deep Pentest Skill !License: MIThttps://img.shields.io/bad...

6.2AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/07/17 11:30 a.m.•38 views

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...

5.8AI score
SaveExploits0
GithubExploit
GithubExploit
•added 2026/07/16 11:43 a.m.•96 views

Decepticon-NavMAX

!Englishhttps://img.shields.io/badge/Language-English-blue?s...

6.3AI score
SaveExploits0
OSV
OSV
•added 2026/07/10 11:16 a.m.•15 views

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...

5.1CVSS6.1AI score0.00304EPSS
SaveExploits0References1
OSV
OSV
•added 2026/07/10 10:38 a.m.•13 views

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...

5.1CVSS6.1AI score
SaveExploits0References5
Snyk
Snyk
•added 2026/07/09 11:20 p.m.•8 views

Out-of-bounds Read

Overview Affected versions of this package are vulnerable to Out-of-bounds Read in the BGP OPEN capability parsing process. An attacker can influence peer AS validation and capability negotiation by sending a specially crafted BGP OPEN message with a malformed capability length, causing the parse...

8.2CVSS6.1AI score0.00332EPSS
SaveExploits0References2
The Hacker News
The Hacker News
•added 2026/07/09 5:15 a.m.•33 views

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead. That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls "Friendly Fire. " It works against Anthropic's Claude Cod...

10CVSS6.5AI score0.00804EPSS
SaveExploits0
Positive Technologies
Positive Technologies
•added 2026/07/02 12:00 a.m.•21 views

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...

9.1CVSS6.4AI score0.01467EPSS
SaveExploits2References95
The Hacker News
The Hacker News
•added 2026/06/26 11:30 a.m.•36 views

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...

6.2AI score
SaveExploits0
Rows per page
Query Builder