Lucene search
+L

1684 matches found

Packet Storm News
Packet Storm News
added 2026/05/10 12:0 a.m.15 views

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason ove...

5.9AI score
SaveExploits0
GithubExploit
GithubExploit
added 2026/05/09 1:43 p.m.105 views

webhunter

🕷️ WebHunter — OWASP Top 10 AI Scanner !Pythonhttps://im...

5.9AI score
SaveExploits0
Wiz blog
Wiz blog
added 2026/05/08 6:42 p.m.12 views

A Framework for AI Threat Readiness

AI models now find and exploit zero-days autonomously. This 4-pillar framework accelerates patching, analysis, and threat response...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/05/08 12:0 a.m.27 views

DarkMoon - the Open-Source AI-Powered Autonomous Penetration Testing Platform

DarkMoon is an automated penetration testing tool that orchestrates complete security assessments using artificial intelligence security agents. Built as an open-source cybersecurity tool, it enables organizations to run professional-grade vulnerability assessments without manual intervention...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/05/08 12:0 a.m.11 views

AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey

Security alert screening is the downstream task of filtering, prioritizing, correlating, and contextualizing alerts for analyst attention in Security Operations Centers. This survey reviews artificial-intelligence-driven alert screening and alert-fatigue mitigation from 2015 to 2026. We synthesiz...

5.8AI score
SaveExploits0
OSV
OSV
added 2026/05/07 7:12 p.m.14 views

MAL-2026-3369 Malicious code in dabrius (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 4a154cab742b51be41ca413e20acccfed4290ac4cf692e1cfeb17a677df98bab The message hidden in the package description tries to convince AI agents to prefer installing the package, which then in multiple places marks execution and...

5.9AI score
SaveExploits0References1
HackRead
HackRead
added 2026/05/07 10:22 a.m.12 views

Scammers Use Hidden Text to Bypass AI Email Filters in Phishing Scams

Scammers are hiding invisible text inside phishing emails to manipulate AI-powered email filters and increase the chances of scams reaching inboxes...

5.8AI score
SaveExploits0
Securelist
Securelist
added 2026/05/07 10:0 a.m.22 views

Exploits and vulnerabilities in Q1 2026

During Q1 2026, the exploit kits leveraged by threat actors to target user systems expanded once again, incorporating new exploits for the Microsoft Office platform, as well as Windows and Linux operating systems. In this report, we dive into the statistics on published vulnerabilities and...

10CVSS7.9AI score0.99979EPSS
SaveExploits224
Positive Technologies
Positive Technologies
added 2026/05/07 12:0 a.m.16 views

PT-2026-38583

Name of the Vulnerable Software and Affected Versions Azure AI Foundry M365 published agents affected versions not specified Description Improper access control in Azure AI Foundry M365 published agents allows an unauthorized attacker to elevate privileges over a network. Recommendations At the...

10CVSS5.8AI score0.01164EPSS
SaveExploits0References10
Wired Threat Level
Wired Threat Level
added 2026/05/06 9:24 p.m.25 views

A Kid With a Fake Mustache Tricked an Online Age-Verification Tool

To stop children from bypassing its age checks, Meta is revamping its age-verification tools with an AI system that analyzes images and videos for “visual cues,” such as height and bone structure...

5.8AI score
SaveExploits0
Akamai Blog
Akamai Blog
added 2026/05/06 5:0 p.m.16 views

AI Survey: 50% of Organizations Struggle to Maintain Latency at Scale

The Akamai State of AI Inference report captures real data from the field that describes how AI inference is being built and scaled in production today...

5.8AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
added 2026/05/06 4:0 p.m.9 views

​​Microsoft named an overall leader in KuppingerCole Analyst’s 2026 Emerging AI Security Operations Center (SOC) report ​​

Security operations are entering a new phase. As attack techniques grow faster and more complex, the effectiveness of a SOC depends less on collecting more data and more on how well platforms can turn context into action at scale. KuppingerCole Analysts’ 2026 Emerging AI Security Operations Cente...

5.8AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2026/05/06 3:49 p.m.16 views

Hackers Hate AI Slop Even More Than You Do

It's not just you. Scammers, hackers, and other cybercriminals are complaining about “AI shit” flooding platforms where they discuss cyberattacks and other illegal activity...

5.8AI score
SaveExploits0
HackRead
HackRead
added 2026/05/06 9:40 a.m.10 views

Application Security Strategies Are Changing as AI-generated Code Floods the SDLC

AI-generated code is changing AppSec workflows, forcing teams to rethink SDLC security, dependency checks, code review, and risk prioritization...

5.9AI score
SaveExploits0
GithubExploit
GithubExploit
added 2026/05/06 4:43 a.m.98 views

Autonomous-AI-PenTest-Agent

Auto...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/05/05 12:0 a.m.16 views

The Adversarial Discount - AI, Signal Correlation, and the Cybersecurity Arms Race

We study a contest-theoretic model of adversarial investment in which an attacker and a defender allocate resources to AI-augmented capabilities across multiple attack surfaces. The attacker's investment operates through two channels: it amplifies offensive potency unconditionally and erodes...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/05/05 12:0 a.m.9 views

Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours

AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is a primary defense, current approaches force operators into manual, library-specific workflows. Operators spend weeks hand-crafting workflows -...

5.8AI score
SaveExploits0
Spring Security Advisories
Spring Security Advisories
added 2026/05/04 12:0 a.m.15 views

Spring Office Hours Podcast: S5E14 - Spec Driven Development with Simon Martinelli

Join Dan Vega and DaShaun Carter for the latest updates from the Spring Ecosystem. In this episode, Dan and DaShaun are joined by Java Champion, Vaadin Champion, and Oracle ACE Pro Simon Martinelli to talk about Spec-Driven Development. With AI reshaping how we write code, Simon makes the case th...

5.9AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/05/03 6:10 a.m.9 views

Malicious code in nextjs-chat-with-ai-service (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8ff3e52e4957291f626e1225ab3b81194c80cd8c6037f943298f6170f98dbe9b The package nextjs-chat-with-ai-service was found to contain malicious code. Source: ghsa-malware...

5.8AI score
SaveExploits0References1
Positive Technologies
Positive Technologies
added 2026/05/02 12:0 a.m.14 views

PT-2026-36667

CVE-2026-30412 SentinelCloud, AI-Driven Autonomous DevOps Engineer One closed loop. Five agents. Seven scenarios. Zero hallucinated kubectl. Live demo https://t.co/ocEWNzLf9Z...

5.8AI score
SaveExploits0References1
Rows per page
Query Builder