Lucene search
+L

16 matches found

Kitploit
Kitploit
•added 2026/10/15 1:04 p.m.•28 views

SBOM-VEX-Taint-Analysis

SBOM → VEX Agent Automatically generate signed CycloneDX VEX documents from SBOMs using a secure multi-agent AI pipeline, built in accordance with the OWASP GenAI Security Project guidelines. The Problem Generating an SBOM surfaces hundreds of CVEs. In practice, over 90% are not exploitable in a...

6.2AI score
SaveExploits0References1
Cvelist
Cvelist
•added 2026/09/04 2:32 p.m.•38 views

CVE-2026-85667 xiaobei through 5.5.2 Unauthenticated Webhook Message Injection

xiaobei through 5.5.2 fails to implement authentication or signature validation on webhook endpoints, allowing unauthenticated attackers to inject arbitrary messages into the agent pipeline. Attackers can publish malicious messages via the /webhookworktool handler and exploit unvalidated media UR...

9.3CVSS0.00695EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
•added 2026/09/04 12:00 a.m.•25 views

PT-2026-85560

xiaobei through 5.5.2 fails to implement authentication or signature validation on webhook endpoints, allowing unauthenticated attackers to inject arbitrary messages into the agent pipeline. Attackers can publish malicious messages via the /webhook worktool handler and exploit unvalidated media U...

9.3CVSS6AI score0.00695EPSS
SaveExploits0References5
GithubExploit
GithubExploit
•added 2026/09/02 9:11 a.m.•26 views

my-dshrness-aipentest

DSH PenTest Workflow v4.2 A multi-agent penetration testing w...

6AI score
SaveExploits0
Wiz blog
Wiz blog
•added 2026/08/27 3:52 p.m.•17 views

From Concept to Context Engine: How Wiz Built AI-Powered Data Discovery

Inside the multi-agent pipeline and feedback loops that turned a bucket scanner into a context engine...

5.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/07/22 12:00 a.m.•21 views

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models LLMs demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight...

5.4AI score
SaveExploits0
OSV
OSV
•added 2026/07/02 7:38 p.m.•24 views

CVE-2026-58579 RAGFlow < 0.26.3 - Stored Cross-Site Scripting via Agent Pipeline Node Name

RAGFlow before 0.26.3 stores an agent pipeline DSL node name without sanitization: the agent update endpoint normalizes the submitted DSL via normalizedsl, which only performs JSON serialization validation and preserves the node name verbatim. The dataflow-result web UI then renders that name int...

5.1CVSS6.1AI score
SaveExploits0References8
Cvelist
Cvelist
•added 2026/07/02 7:38 p.m.•59 views

CVE-2026-58579 RAGFlow < 0.26.3 - Stored Cross-Site Scripting via Agent Pipeline Node Name

RAGFlow before 0.26.3 stores an agent pipeline DSL node name without sanitization: the agent update endpoint normalizes the submitted DSL via normalizedsl, which only performs JSON serialization validation and preserves the node name verbatim. The dataflow-result web UI then renders that name int...

5.4CVSS0.00298EPSS
SaveExploits0References5
Vulnrichment
Vulnrichment
•added 2026/07/02 7:38 p.m.•35 views

CVE-2026-58579 RAGFlow < 0.26.3 - Stored Cross-Site Scripting via Agent Pipeline Node Name

RAGFlow before 0.26.3 stores an agent pipeline DSL node name without sanitization: the agent update endpoint normalizes the submitted DSL via normalizedsl, which only performs JSON serialization validation and preserves the node name verbatim. The dataflow-result web UI then renders that name int...

5.4CVSS6AI score0.00298EPSS
SaveExploits0References5
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/07/02 12:00 a.m.•9 views

CVE-2026-58579: Improper Neutralization of Input During Web Page Generation

RAGFlow before 0.26.3 stores an agent pipeline DSL node name without sanitization: the agent update endpoint normalizes the submitted DSL via normalizedsl, which only performs JSON serialization validation and preserves the node name verbatim. The dataflow-result web UI then renders that name int...

5.4CVSS6AI score0.00298EPSS
SaveExploits0References2
Mend
Mend
•added 2026/06/16 6:05 p.m.•9 views

CVE-2026-53851

OpenClaw before 2026.5.12 contains a notification bypass vulnerability allowing Slack reaction events to enter the agent pipeline despite disabled reaction notifications. Attackers can trigger unintended agent processing by sending reaction events when the feature is enabled, potentially leading ...

6.3CVSS5.9AI score0.00324EPSS
SaveExploits0References5
Cvelist
Cvelist
•added 2026/06/16 6:05 p.m.•41 views

CVE-2026-53851 OpenClaw < 2026.5.12 - Slack Reaction Event Notification Bypass

OpenClaw before 2026.5.12 contains a notification bypass vulnerability allowing Slack reaction events to enter the agent pipeline despite disabled reaction notifications. Attackers can trigger unintended agent processing by sending reaction events when the feature is enabled, potentially leading ...

6.3CVSS0.00324EPSS
SaveExploits0References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/06/16 12:00 a.m.•9 views

CVE-2026-53851: Missing Authorization

OpenClaw before 2026.5.12 contains a notification bypass vulnerability allowing Slack reaction events to enter the agent pipeline despite disabled reaction notifications. Attackers can trigger unintended agent processing by sending reaction events when the feature is enabled, potentially leading ...

6.3CVSS5.9AI score0.00324EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
•added 2026/06/16 12:00 a.m.•33 views

PT-2026-49768

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.5.12 Description A notification bypass allows Slack reaction events to enter the agent pipeline even when reaction notifications are disabled. This can trigger unintended agent processing for reaction events,...

6.3CVSS5.8AI score0.00324EPSS
SaveExploits0References5
Wordfence Blog
Wordfence Blog
•added 2026/04/10 4:18 p.m.•25 views

The Increasing Role of AI in Vulnerability Research

At Wordfence, we run a bug bounty program that pays out mid-six figures per year to researchers in bug bounties for WordPress related vulnerabilities. Funding this research helps us improve security for the WordPress community overall, and helps us secure our customers by rolling out protection f...

5.8AI score
SaveExploits0
Positive Technologies
Positive Technologies
•added 2026/02/17 12:00 a.m.•31 views

PT-2026-23527

Name of the Vulnerable Software and Affected Versions OpenClaw versions 2026.1.29 through 2026.2.0 Description The OpenClaw software, with the Twitch plugin installed and enabled, has an issue where access control is bypassed. Specifically, the allowFrom allowlist is not properly enforced when...

7.3CVSS5.9AI score0.00558EPSS
SaveExploits1References8
Rows per page
Query Builder