Lucene search
+L

7105 matches found

CNNVD
CNNVD
added 2026/06/01 12:0 a.m.19 views

Hermes Agent 安全漏洞

Hermes Agent is an AI agent tool developed by Nous Research, featuring a self-learning mechanism. Versions of Hermes Agent prior to 2026.4.30 contained a security vulnerability, which was caused by issues with the servepluginskill/skillview function in the tools/skillstool.py file. This...

7.5CVSS7.3AI score0.00304EPSS
Exploits0References5
Metasploit
Metasploit
added 2026/05/31 7:2 p.m.293 views

Windows Kernel Pointer Exposure Enumerator

This module enumerates kernel object pointers exposed via NtQuerySystemInformation with SystemExtendedHandleInformation. It categorizes exposed pointers by object type and provides observational data about kernel address space layout for research and educational purposes. Module Options msf use...

5.9AI score
Exploits0
GithubExploit
GithubExploit
added 2026/05/31 6:16 p.m.115 views

Exploit for CVE-2022-42005

Tesla Security Research Vulnerability research on the Tesla M...

6.2AI score
Exploits1
Packet Storm News
Packet Storm News
added 2026/05/31 12:0 a.m.21 views

Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research

The attack surface of a modern operating system is a haystack: thousands of signed binaries and millions of functions, almost none relevant to any given vulnerability. A human analyst or an LLM agent must pick the function worth reading before analyzing it. At whole-OS scope, this target selectio...

5.8AI score
Exploits0
Packet Storm News
Packet Storm News
added 2026/05/31 12:0 a.m.36 views

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection. ClawHub Security Signals is a sanitized dataset of 67,453 latest public OpenClaw skill...

5.8AI score
Exploits0
GithubExploit
GithubExploit
added 2026/05/30 12:26 a.m.142 views

Exploit for CVE-2025-66478

CVE-2025-66478-Research-Proof-of-Concept Overview This re...

7.5AI score
Exploits111
RedhatCVE
RedhatCVE
added 2026/05/29 8:13 p.m.15 views

CVE-2026-46526

Local Deep Research is an AI-powered research assistant for deep, iterative research. Prior to 1.6.10, the URL checking logic in local-deep-research has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. The current project uses validateurl to validate the input URL. The...

5CVSS5.8AI score0.00247EPSS
Exploits0References1
ATTACKERKB
ATTACKERKB
added 2026/05/29 1:30 p.m.10 views

CVE-2026-45611

Further research determined the issue is not a vulnerability...

5.8AI score
Exploits0References1
GithubExploit
GithubExploit
added 2026/05/29 8:35 a.m.152 views

Y2X

Y2eXploit Y2X --- Overview Y2eXploit Y2X is an a...

5.9AI score
Exploits0
GithubExploit
GithubExploit
added 2026/05/29 6:28 a.m.107 views

sqli_exploit

S...

5.8AI score
Exploits0
OSV
OSV
added 2026/05/28 7:18 p.m.12 views

GHSA-G23J-2VWM-5C25 local-deep-research has an SSRF bypass in `safe_get`

Summary The URL checking logic in local-deep-research has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. Details The current project uses validateurl to validate the input URL. The main logic is to perform security checks on the host portion of the URL extracted by...

5CVSS5.9AI score0.00247EPSS
Exploits0References8
NVD
NVD
added 2026/05/28 7:16 p.m.20 views

CVE-2026-46526

Local Deep Research is an AI-powered research assistant for deep, iterative research. Prior to 1.6.10, the URL checking logic in local-deep-research has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. The current project uses validateurl to validate the input URL. The...

5CVSS0.00247EPSS
Exploits0References6
ATTACKERKB
ATTACKERKB
added 2026/05/28 5:59 p.m.12 views

CVE-2026-43979

Local Deep Research is an AI-powered research assistant for deep, iterative research. Prior to 1.6.0, PDFService.markdowntohtml constructs an HTML document by interpolating user-controlled values — specifically title sourced from research.title or research.query and metadata key-value pairs —...

5CVSS5.9AI score0.00263EPSS
Exploits0References4Affected Software1
CVE
CVE
added 2026/05/28 5:58 p.m.39 views

CVE-2026-46526

CVE-2026-46526 concerns Local Deep Research. Before version 1.6.10, the URL validation flow had a logical flaw that could bypass SSRF protections because parsing differed between urlparse and the HTTP request library. The code first runs SSRF checks via validate_url and then uses requests.get to ...

5CVSS5.8AI score0.00247EPSS
Exploits0References6
Cvelist
Cvelist
added 2026/05/28 5:58 p.m.39 views

CVE-2026-46526 Local Deep Research: SSRF bypass in `safe_get`

Local Deep Research is an AI-powered research assistant for deep, iterative research. Prior to 1.6.10, the URL checking logic in local-deep-research has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. The current project uses validateurl to validate the input URL. The...

5CVSS0.00247EPSS
Exploits0References6
Vulnrichment
Vulnrichment
added 2026/05/28 5:58 p.m.11 views

CVE-2026-46526 Local Deep Research: SSRF bypass in `safe_get`

Local Deep Research is an AI-powered research assistant for deep, iterative research. Prior to 1.6.10, the URL checking logic in local-deep-research has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. The current project uses validateurl to validate the input URL. The...

5CVSS5.8AI score0.00247EPSS
Exploits0References6
EUVD
EUVD
added 2026/05/28 5:58 p.m.13 views

EUVD-2026-32977

Local Deep Research is an AI-powered research assistant for deep, iterative research. Prior to 1.6.10, the URL checking logic in local-deep-research has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. The current project uses validateurl to validate the input URL. The...

5CVSS5.8AI score0.00247EPSS
Exploits0References6
OSV
OSV
added 2026/05/28 5:58 p.m.4 views

CVE-2026-46526 Local Deep Research: SSRF bypass in `safe_get`

Local Deep Research is an AI-powered research assistant for deep, iterative research. Prior to 1.6.10, the URL checking logic in local-deep-research has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. The current project uses validateurl to validate the input URL. The...

5CVSS6AI score0.00247EPSS
Exploits0References8
CNNVD
CNNVD
added 2026/05/28 12:0 a.m.10 views

Local Deep Research 安全漏洞

Local Deep Research is an AI search assistant developed by LearningCircuit. Versions prior to 1.6.0 of Local Deep Research contained a security vulnerability. This vulnerability stemmed from PDFService.markdowntohtml not properly escaping user-controlled values, allowing authentication attackers ...

5CVSS5.9AI score0.00263EPSS
Exploits0References3
Positive Technologies
Positive Technologies
added 2026/05/28 12:0 a.m.21 views

PT-2026-44472

Name of the Vulnerable Software and Affected Versions local-deep-research versions prior to 1.6.10 Description A logical flaw in the URL checking logic allows attackers to bypass security filters, leading to Server-Side Request Forgery SSRF. The software uses the validate url function to perform...

5CVSS6.1AI score0.00247EPSS
Exploits0References16
Rows per page
Query Builder