Lucene search
+L

800 matches found

HackRead
HackRead
added 2025/11/14 4:6 p.m.7 views

Chinese State Hackers Jailbroke Claude AI Code for Automated Breaches

Anthropic, the developer behind Claude AI, says a Chinese state sponsored group used its model to automate most of a cyber espionage operation against about 30 companies with Claude handling up to 90% of the technical work...

6.9AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/11/14 9:53 a.m.12 views

Chinese Hackers Use Anthropic's AI to Launch Automated Cyber Espionage Campaign

State-sponsored threat actors from China used artificial intelligence AI technology developed by Anthropic to orchestrate automated cyber attacks as part of a "highly sophisticated espionage campaign" in mid-September 2025. "The attackers used AI's 'agentic' capabilities to an unprecedented degre...

7.1AI score
SaveExploits0
Trend Micro Simply Security
Trend Micro Simply Security
added 2025/11/14 12:0 a.m.8 views

Redefining Enterprise Defense in the Era of AI-Led Cyberattacks

More cybercriminals are turning to using autonomous AI tools to upgrade their attacks, as exemplified by the recent utilization of Anthropic’s Claude Code, prompting an urgent need for enterprises to adopt agentic AI-driven security platforms and proactive defenses to counter AI-related threats...

7AI score
SaveExploits0
Snyk
Snyk
added 2025/11/07 3:58 a.m.3 views

Malicious Package

Overview @chatclub/claude-code is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

9.8CVSS6.8AI score
SaveExploits0References2
EUVD
EUVD
added 2025/11/07 3:58 a.m.3 views

EUVD-2025-38230

Malicious code in @chatclub/claude-code npm...

6.6AI score
SaveExploits0References1
OSV
OSV
added 2025/11/07 3:58 a.m.3 views

MAL-2025-49379 Malicious code in @chatclub/claude-code (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b6acfccb78a615c7f037fe5dbd1001d9a77ca4015c89c94122ba5dd78978b66b The package @chatclub/claude-code was found to contain malicious code. Source: ghsa-malware...

6.9AI score
SaveExploits0References3
Veracode
Veracode
added 2025/11/06 9:18 a.m.10 views

Arbitrary Code Execution

@anthropic-ai/claude-code is vulnerable to Arbitrary Code Execution. The vulnerability is due to the automatic execution of Yarn plugins when running yarn --version, which allows an attacker to bypass the directory trust dialog and execute code before the user confirms trust in the directory...

9.8CVSS7.7AI score0.00341EPSS
SaveExploits0References5Affected Software1
OSV
OSV
added 2025/11/06 9:16 a.m.11 views

USN-7862-1 linux, linux-aws, linux-aws-5.15, linux-gcp, linux-gcp-5.15, linux-gke, linux-gkeop, linux-hwe-5.15, linux-ibm, linux-ibm-5.15, linux-intel-iotg, linux-intel-iotg-5.15, linux-lowlatency, linux-lowlatency-hwe-5.15, linux-nvidia, linux-oracle, linux-oracle-5.15 vulnerability

Jean-Claude Graf, Sandro Rüegge, Ali Hajiabadi, and Kaveh Razavi discovered that the Linux kernel contained insufficient branch predictor isolation between a guest and a userspace hypervisor for certain processors. This flaw is known as VMSCAPE. An attacker in a guest VM could possibly use this t...

5.5CVSS5.8AI score0.00331EPSS
SaveExploits0References2
Spring Security Advisories
Spring Security Advisories
added 2025/10/30 12:0 a.m.19 views

AWS Bedrock Prompt Caching Support in Spring AI

In our previous blog post about Anthropic prompt caching, we explored how prompt caching dramatically reduces API costs and latency by reusing previously processed prompt content. We introduced Spring AI's five strategic caching patterns for Anthropic Claude models and showed how they automatical...

7.2AI score
SaveExploits0
EUVD
EUVD
added 2025/10/27 7:29 a.m.2 views

EUVD-2025-36128

Malicious code in @chatgptclaudeclub/claude-code npm...

6.6AI score
SaveExploits0References1
Snyk
Snyk
added 2025/10/27 7:29 a.m.3 views

Malicious Package

Overview @chatgptclaudeclub/claude-code is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and thi...

9.8CVSS6.8AI score
SaveExploits0References2
EUVD
EUVD
added 2025/10/27 7:13 a.m.3 views

EUVD-2025-36117

Malicious code in bad-santa-claude npm...

6.6AI score
SaveExploits0References1
Spring Security Advisories
Spring Security Advisories
added 2025/10/27 12:0 a.m.8 views

Prompt Caching Support in Spring AI with Anthropic Claude

Large language model API costs can accumulate quickly when applications repeatedly send the same prompt content. A typical scenario: you're building a document analyzer that includes a 3,000-token document in every request. Five questions about that document means processing 15,000 tokens of...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/24 12:0 a.m.47 views

Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models

Large language models LLMs remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker mode...

7AI score
SaveExploits0
HackRead
HackRead
added 2025/10/23 5:28 p.m.9 views

Shadow Escape 0-Click Attack in AI Assistants Puts Trillions of Records at Risk

Operant AI reveals Shadow Escape, a zero-click attack using the MCP flaw in ChatGPT, Gemini, and Claude to secretly steal trillions of SSNs and financial data. Traditional security is blind to this new AI threat...

6.9AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/10/23 9:0 a.m.4 views

Malicious code in bad-santa-claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 2f3ae5211cbede196c8612c8e14c54147ab8c3984a6d1d26675336e526316bae Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

6.8AI score
SaveExploits0References1
OSV
OSV
added 2025/10/23 9:0 a.m.4 views

MAL-2025-48782 Malicious code in bad-santa-claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 2f3ae5211cbede196c8612c8e14c54147ab8c3984a6d1d26675336e526316bae Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

6.8AI score
SaveExploits0References1
Wired Threat Level
Wired Threat Level
added 2025/10/20 9:0 a.m.3 views

Anthropic Has a Plan to Keep Its AI From Building a Nuclear Weapon. Will It Work?

Anthropic partnered with the US government to create a filter meant to block Claude from helping someone build a nuke. Experts are divided on whether its a necessary protection—or a protection at all...

6.9AI score
SaveExploits0
NVD
NVD
added 2025/10/03 8:15 p.m.7 views

CVE-2025-59829

Claude Code is an agentic coding tool. Versions below 1.0.120 failed to account for symlinks when checking permission deny rules. If a user explicitly denied Claude Code access to a file and Claude Code had access to a symlink pointing to that file, it was possible for Claude Code to access the...

6.5CVSS0.00396EPSS
SaveExploits0References1
EUVD
EUVD
added 2025/10/03 8:7 p.m.7 views

EUVD-2025-32229

Malicious code in bioql PyPI...

8.7CVSS6.6AI score0.30227EPSS
SaveExploits6References2
Rows per page
Query Builder