Claude AI Exploited to Operate 100+ Fake Political Personas in Global Influence Campaign

Artificial intelligence AI company Anthropic has revealed that unknown threat actors leveraged its Claude chatbot for an "influence-as-a-service" operation to engage with authentic accounts across Facebook and X. The sophisticated activity, branded as financially-motivated, is said to have used i...

The Hidden Risks of LLM-Generated Web Application Code: a Security-Centric Evaluation of Code Generation Capabilities in Large Language Models

The rapid advancement of Large Language Models LLMs has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code generated by LLMs has been shown to generate insecure code in...

Using Spring AI 1.0.0-SNAPSHOT: Important Changes and Updates

Using Spring AI 1.0.0-SNAPSHOT: Important Changes and Updates Spring AI 1.0.0-SNAPSHOT introduces several important changes to artifact IDs, dependency management, and autoconfiguration. This blog post outlines these changes and provides guidance on how to update your projects. The most significa...

agentic-fleet (>=0.1.6 <=0.4.81), composio (=0.1.1) +37 more potentially affected by CVE-2024-8952 via composio-core (>=0.3.13 <=0.7.21)

composio-core PYPI version =0.3.13, =0.1.6, =0.7.1, =0.3.13, =0.3.17, =0.3.13, =0.3.13, =0.7.1, =0.5.26, =0.3.13, =0.3.13, =0.3.13, =0.3.24, =0.7.15, =0.3.13, =0.7.20 and more Source cves: CVE-2024-8952 Source advisory: SNYK:PYTHON-COMPOSIOCORE-9637813...

composio-autogen (>=0.3.13 <=0.5.42), composio-camel (>=0.3.17 <=0.5.42) +13 more potentially affected by CVE-2024-8953 via composio-core (>=0.3.13 <=0.5.42)

composio-core PYPI version =0.3.13, =0.3.13, =0.3.17, =0.3.13, =0.3.13, =0.5.26, =0.3.13, =0.3.13, =0.3.13, =0.3.24, =0.3.13, =0.3.13, =0.3.13, =0.4.2, =0.3.24, =0.2.31, =0.2.40 Source cves: CVE-2024-8953 Source advisory: SNYK:PYTHON-COMPOSIOCORE-9637814...

CVE-2024-53526

composio =0.5.40 is vulnerable to Command Execution in composioopenai, composioclaude, and composiojulep via the handletoolcalls function...

Imperva Defends Against LLM Hacking

In the evolving landscape of cybersecurity, the advent of large language models LLMs has introduced a new frontier of challenges and opportunities. Research has shown advanced LLMs, such as GPT-4, now possess the ability to autonomously execute sophisticated cyberattacks, including blind database...

Malicious Package

Overview claudeai-eng is a malicious package. This package mimics a tool for working with Claude, silently exfiltrating data and compromising developer environments. Remediation Avoid using all malicious instances of the claudeai-eng package. References - Vulnerability Report Credit: Leonid...

PyPI Attack: ChatGPT, Claude Impersonators Deliver JarkaStealer via Python Libraries

Cybersecurity researchers have discovered two malicious packages uploaded to the Python Package Index PyPI repository that impersonated popular artificial intelligence AI models like OpenAI ChatGPT and Anthropic Claude to deliver an information stealer called JarkaStealer. The packages, named...

AI/LLM Claude Sonnet API Detection

Binary data 701487.prm...

composio-autogen (>=0.3.13 <=0.5.52rc2), composio-camel (>=0.3.17 <=0.5.52rc2) +15 more potentially affected by CVE-2024-8865 via composio-core (>=0.3.13 <=0.5.8)

composio-core PYPI version =0.3.13, =0.3.13, =0.3.17, =0.3.13, =0.3.13, =0.5.26, =0.3.13, =0.3.13, =0.3.13, =0.3.24, =0.3.13, =0.3.13, =0.3.13, =0.4.2, =0.3.24, =0.5.43 - gensphere =0.1.9 and more Source cves: CVE-2024-8865 Source advisory: OSV:GHSA-66R2-XM28-74W9...

MAL-2024-2189 Malicious code in down_load_ebook_jefferson_by_jean_claude_mourlevat_3k9y4 (npm)

--- -= Per source details. Do not edit below this line.=-...

claude-hammer.fr Cross Site Scripting vulnerability OBB-3929946

Following the coordinated and responsible vulnerability disclosure guidelines of the ISO 29147 standard, Open Bug Bounty has: a. verified the vulnerability and confirmed its existence; b. notified the website operator about its existence. Technical details of the vulnerability are currently hidde...

Jailbreaking LLMs with ASCII Art

Researchers have demonstrated that putting words in ASCII art can cause LLMs--GPT-3.5, GPT-4, Gemini, Claude, and Llama2--to ignore their safety instructions. Research paper...

claudeberger.fr Cross Site Scripting vulnerability OBB-1311531

Following coordinated and responsible vulnerability disclosure guidelines of the ISO 29147 standard, Open Bug Bounty has: &nbsp&nbsp&nbsp&nbsp&nbsp&nbspa. verified the vulnerability and confirmed its existence; &nbsp&nbsp&nbsp&nbsp&nbsp&nbspb. notified the website operator about its existence...

claude-verlinde.fr Cross Site Scripting vulnerability

Security Researcher geeknik Helped patch 8562 vulnerabilities Received 8 Coordinated Disclosure badges Received 20 recommendations , a holder of 8 badges for responsible and coordinated disclosure, found a security vulnerability affecting claude-verlinde.fr website and its users. Following...

claudesaulnier.eu XSS vulnerability

Vulnerable URL: http://www.claudesaulnier.eu/w/llink.cfm?wy=4u=javascript:alert%28/OPENBUGBOUNTY/%29t= Details: Description| Value ---|--- Patched:| No Latest check for patch:| 30.07.2017 Vulnerability type:| XSS Vulnerability status:| Publicly disclosed Alexa Rank| Unknown / Not calculated VIP...

claudechabrol.entcreuse.fr XSS vulnerability

Vulnerable URL: http://claudechabrol.entcreuse.fr/sg.do Details: Description| Value ---|--- Patched:| Yes, at 02.03.2017 Latest check for patch:| 02.03.2017 12:30 GMT Vulnerability type:| XSS Vulnerability status:| Publicly disclosed Alexa Rank| Unknown / Not calculated VIP website status:| No...

claude-monet.ent27.fr XSS vulnerability

Vulnerable URL: http://claude-monet.ent27.fr/sg.do Details: Description| Value ---|--- Patched:| Yes, at 02.03.2017 Latest check for patch:| 02.03.2017 12:15 GMT Vulnerability type:| XSS Vulnerability status:| Publicly disclosed Alexa Rank| 182427 VIP website status:| No Coordinated Disclosure...

jean-claude-aubry.elycee.rhonealpes.fr XSS vulnerability

Vulnerable URL: http://jean-claude-aubry.elycee.rhonealpes.fr/sg.do Details: Description| Value ---|--- Patched:| Yes, at 28.07.2017 Latest check for patch:| 28.07.2017 11:56 GMT Vulnerability type:| XSS Vulnerability status:| Publicly disclosed Alexa Rank| Unknown / Not calculated VIP website...