Lucene search
+L

255 matches found

Imperva Blog
Imperva Blog
added 2 days ago9 views

The OWASP LLM Top 10 Was the Warm-Up: What Comes Next

When the OWASP Top 10 for LLM Applications arrived, it did the industry a real service. It gave security teams a stable, vendor-neutral vocabulary for a threat surface that was moving too fast to describe. Prompt injection, sensitive information disclosure, system prompt leakage, improper output...

6.2AI score
SaveExploits0
NVD
NVD
added 2026/08/05 7:17 p.m.11 views

CVE-2026-9196

IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user...

8.8CVSS0.00265EPSS
SaveExploits0References1
OSV
OSV
added 2026/08/05 7:17 p.m.7 views

CVE-2026-9196

IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user...

8.8CVSS5.6AI score
SaveExploits0References1
ATTACKERKB
ATTACKERKB
added 2026/08/05 6:27 p.m.10 views

CVE-2026-9196

IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user...

8.1CVSS5.7AI score0.00265EPSS
SaveExploits0References2Affected Software1
CVE
CVE
added 2026/08/05 6:27 p.m.64 views

CVE-2026-9196

IBM Langflow OSS 1.0.0–1.10.3 is affected by an authenticated code-execution risk during Agentic Assistant validation caused by improper handling of LLM-generated components. The backend may execute model-generated Python code in the validation step before user approval, enabling an attacker to t...

8.8CVSS5.7AI score0.00265EPSS
SaveExploits0References1Affected Software1
Imperva Blog
Imperva Blog
added 2026/08/05 12:32 p.m.29 views

Agentic AI Security: The Chatbot Era Is Already Over

There is a diagram most security teams still carry in their heads when they think about AI. A user talks to a chatbot. The chatbot talks to a large language model. The model talks back. Put an inspection point in the middle, and the problem is solved. That diagram was accurate for about eighteen...

6AI score
SaveExploits0
Spring Security Advisories
Spring Security Advisories
added 2026/08/04 12:0 a.m.21 views

This Week in Spring - August 4th, 2026

Hi, Spring fans! Welcome to another installment of This Week in Spring! It's the 4th of August! We're already in month eight of this year! Great Scott! This is an interesting project to help ensure idempotency keys for Spring Boot requests A very interesting post on The New Stack titled, When...

5.5AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
added 2026/07/30 4:0 p.m.10 views

​​​​What’s new in Microsoft Security: July 2026

Every organization needs security that protects end to end with the speed and scale of AI. Microsoft’s vision is simple: security should be ambient and autonomous, just like the AI it protects. As organizations scale AI and expand across environments, security teams need protection that covers...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/07/29 12:0 a.m.10 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
Vulnrichment
Vulnrichment
added 2026/07/20 10:1 p.m.8 views

CVE-2026-57494 AgenticMail: Cross-agent task authorization bypass in AgenticMail API

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

7.1CVSS5.3AI score0.0022EPSS
SaveExploits0References1
NVD
NVD
added 2026/07/17 8:17 p.m.14 views

CVE-2026-15995

IBM Cognos Analytics 12.1.3 GA Version with build number through 12.1.3-2606251736 could allow an attacker to obtain incorrect report summary results or cause report-processing failures due to a race condition in the Agentic AI assistant's concurrent request-handling logic when multiple...

5.4CVSS0.00101EPSS
SaveExploits0References1
CVE
CVE
added 2026/07/17 7:34 p.m.48 views

CVE-2026-15995

Summary of CVE-2026-15995 : IBM Cognos Analytics 12.1.3 GA (build up to 12.1.3-2606251736) contains a race condition in the Agentic AI assistant’s concurrent request handling. Under certain concurrent usage, two authenticated users submitting the same action can cause incorrect report summaries o...

5.4CVSS5.3AI score0.00101EPSS
SaveExploits0References1Affected Software1
Cvelist
Cvelist
added 2026/07/17 7:34 p.m.49 views

CVE-2026-15995 IBM Cognos Analytics 12.1.3 general availability package contains a data integrity issue in the Agentic AI assistant that may cause incorrect report summaries or report-processing errors under concurrent use

IBM Cognos Analytics 12.1.3 GA Version with build number through 12.1.3-2606251736 could allow an attacker to obtain incorrect report summary results or cause report-processing failures due to a race condition in the Agentic AI assistant's concurrent request-handling logic when multiple...

5.4CVSS0.00101EPSS
SaveExploits0References1
EUVD
EUVD
added 2026/07/17 7:34 p.m.17 views

EUVD-2026-45294

IBM Cognos Analytics 12.1.3 GA Version with build number through 12.1.3-2606251736 could allow an attacker to obtain incorrect report summary results or cause report-processing failures due to a race condition in the Agentic AI assistant's concurrent request-handling logic when multiple...

5.4CVSS5.3AI score0.00101EPSS
SaveExploits0References1
ATTACKERKB
ATTACKERKB
added 2026/07/17 7:34 p.m.14 views

CVE-2026-15995

IBM Cognos Analytics 12.1.3 GA Version with build number through 12.1.3-2606251736 could allow an attacker to obtain incorrect report summary results or cause report-processing failures due to a race condition in the Agentic AI assistant's concurrent request-handling logic when multiple...

5.4CVSS5.3AI score0.00101EPSS
SaveExploits0References2
NVD
NVD
added 2026/07/17 7:17 p.m.12 views

CVE-2026-58195

Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts,...

8.8CVSS0.00456EPSS
SaveExploits0References7
Vulnrichment
Vulnrichment
added 2026/07/17 6:47 p.m.21 views

CVE-2026-58195 Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync

Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts,...

8.8CVSS5.8AI score0.00456EPSS
SaveExploits0References7
Cvelist
Cvelist
added 2026/07/17 6:47 p.m.55 views

CVE-2026-58195 Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync

Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts,...

8.8CVSS0.00456EPSS
SaveExploits0References7
ATTACKERKB
ATTACKERKB
added 2026/07/17 6:47 p.m.8 views

CVE-2026-58195

Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts,...

8.8CVSS5.8AI score0.00456EPSS
SaveExploits0References8Affected Software1
EUVD
EUVD
added 2026/07/17 6:47 p.m.13 views

EUVD-2026-45256

Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts,...

8.8CVSS5.9AI score0.00456EPSS
SaveExploits0References7
Rows per page
Query Builder