Lucene search
+L

1085 matches found

Schneier on Security
Schneier on Security
added 2 days ago8 views

Anthropic’s Opus 5 Is Better at Resisting Prompt Injection

The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 5.9% at k=15 and Mythos 5 2.6%, making it the most robust model...

5.5AI score
SaveExploits0
GithubExploit
GithubExploit
added 2 days ago54 views

Exploit for CVE-2026-17351

CVE-2026-17351 — pgAdmin 4 AI Assistant Read-Only Bypass via L...

9.4CVSS6AI score0.00447EPSS
SaveExploits1
CVE
CVE
added 2 days ago15 views

CVE-2026-17351

The CVE-2026-17351 issue affects pgAdmin 4 (versions from 9.13 up to, but not including, 9.17). The vulnerability stems from a mismatch between sqlparse’s string-literal handling and PostgreSQL’s parser, which can allow an LLM-supplied query executed inside a BEGIN TRANSACTION READ ONLY wrapper t...

9.4CVSS5.5AI score0.00447EPSS
SaveExploits1References3
Tenable Nessus
Tenable Nessus
added 2 days ago5 views

FreeBSD : Gitlab -- vulnerabilities (661d3db5-8bd9-11f1-9c40-2cf05da270f3)

The version of FreeBSD installed on the remote host is prior to tested version. It is, therefore, affected by multiple vulnerabilities as referenced in the 661d3db5-8bd9-11f1-9c40-2cf05da270f3 advisory. Gitlab reports: Sensitive Information Exposure issue in Workhorse impacts GitLab CE/EE Mass...

8.5CVSS6.2AI score0.00394EPSS
SaveExploits0References15
Packet Storm News
Packet Storm News
added 3 days ago6 views

Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Large Language Model LLM-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction naturalness, it introduces a critical yet under-explored attack surface, as audio inputs inevitably contain...

5.7AI score
SaveExploits0
OSV
OSV
added 6 days ago5 views

CVE-2026-17534 Kimi Code FetchURL SSRF protection bypass via DNS-resolving hostnames and redirects

Kimi Code @moonshot-ai/kimi-code before 0.27.0 implements FetchURL SSRF hardening as a static hostname and IP-literal denylist in assertSafeFetchTarget, without resolving DNS or re-validating hosts after HTTP redirects. An attacker who can influence a FetchURL call for example via prompt injectio...

5.5CVSS5.9AI score0.00121EPSS
SaveExploits0References7
GithubExploit
GithubExploit
added 2026/07/26 11:21 p.m.55 views

DarkPrompt

DarkPrompt !CIhttps://github.com/jason-allen-oneal/DarkPr...

5.9AI score
SaveExploits0
EUVD
EUVD
added 2026/07/24 4:54 p.m.15 views

EUVD-2026-40117

Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution...

8.8CVSS5.9AI score0.00552EPSS
SaveExploits0References3
NVD
NVD
added 2026/07/24 4:16 p.m.10 views

CVE-2026-66027

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

8.7CVSS0.00255EPSS
SaveExploits0References5
EUVD
EUVD
added 2026/07/24 3:27 p.m.7 views

EUVD-2026-48641

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

8.7CVSS6AI score0.00255EPSS
SaveExploits0References5
NVD
NVD
added 2026/07/24 3:19 p.m.8 views

CVE-2026-66004

BlenderMCP before commit 30a3308 contains a path traversal vulnerability in the downloadpolyhavenasset method that allows attackers to write arbitrary files by injecting traversal sequences in API response include keys. Attackers performing MITM attacks or prompt injection can supply malicious...

6CVSS0.00295EPSS
SaveExploits0References4
EUVD
EUVD
added 2026/07/24 2:44 p.m.7 views

EUVD-2026-48604

BlenderMCP before commit 30a3308 contains a path traversal vulnerability in the downloadpolyhavenasset method that allows attackers to write arbitrary files by injecting traversal sequences in API response include keys. Attackers performing MITM attacks or prompt injection can supply malicious...

6CVSS6AI score0.00295EPSS
SaveExploits0References4
Cvelist
Cvelist
added 2026/07/24 2:44 p.m.31 views

CVE-2026-66004 BlenderMCP Path Traversal via download_polyhaven_asset API

BlenderMCP before commit 30a3308 contains a path traversal vulnerability in the downloadpolyhavenasset method that allows attackers to write arbitrary files by injecting traversal sequences in API response include keys. Attackers performing MITM attacks or prompt injection can supply malicious...

6CVSS0.00295EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
added 2026/07/24 12:0 a.m.15 views

PT-2026-64372

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

8.7CVSS6AI score0.00255EPSS
SaveExploits0References6
OSV
OSV
added 2026/07/23 11:41 a.m.9 views

PYSEC-2026-3530 PraisonAI: Server-Side Request Forgery (SSRF) in SearxNG / search_web tools via attacker-controlled searxng_url parameter

Summary A Server-Side Request Forgery SSRF vulnerability in the SearxNG / searchweb search tools allows an attacker to make the server perform requests to arbitrary internal endpoints and read the responses back. The searxngurl argument is passed directly to requests.get with no validation of...

8.8CVSS5.6AI score
SaveExploits0References5
NVD
NVD
added 2026/07/22 12:18 p.m.9 views

CVE-2026-44192

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS0.00149EPSS
SaveExploits0References2
Cvelist
Cvelist
added 2026/07/22 12:6 p.m.34 views

CVE-2026-44192 Ansible-lightspeed: ansible lightspeed mcp server: remote code execution and data exfiltration via path traversal

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS0.00149EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 2026/07/22 12:6 p.m.5 views

CVE-2026-44192 Ansible-lightspeed: ansible lightspeed mcp server: remote code execution and data exfiltration via path traversal

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS5.7AI score0.00149EPSS
SaveExploits0References2
EUVD
EUVD
added 2026/07/22 12:6 p.m.8 views

EUVD-2026-47652

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS5.6AI score0.00149EPSS
SaveExploits0References2
CVE
CVE
added 2026/07/22 12:6 p.m.14 views

CVE-2026-44192

CVE-2026-44192 affects the Ansible Lightspeed Model Context Protocol (MCP) server. The vulnerability is a path traversal flaw that can be triggered to manipulate an AI agent via indirect prompt injection, allowing writing of files to unauthorized locations on the user’s system, which may expose s...

6.6CVSS5.7AI score0.00149EPSS
SaveExploits0References2
Rows per page
Query Builder