490 matches found
synaptic-sentinel
SYNAPTIC Sentinel The vibe-coding security sentinel. An Apache-2.0 agentic security toolkit for projects where most of the code is written by AI. Five deterministic scouts catch the syntactic problems; a Brain Layer BYOK Anthropic decides what really matters and how to fix it — all inside the IDE...
oss-scanner
OSS Scanner OSS Scanner is a service by Anthropic to scan critical open-source repositories for security vulnerabilities. Learn more about the service at red.anthropic.com/oss-scanner. Note, use of this tool is subject to the terms and conditions outlined in the OSS Scanner terms. How to sign up...
Anthropic-Cybersecurity-Skills
Anthropic Cybersecurity Skills The largest open-source cybersecurity skills library for AI agents !Hermes Agenthttps://img.shields...
CVE-2025-54794-Hijacking-Claude-AI-with-a-Prompt-Injection-The-Jailbreak-That-Talked-Back
🧠 CVE-2025-54794: Hijacking Claude AI with a Prompt Injection – The Jailbreak That Talked Back By Aditya Bhatt | Offensive Security Specialist | Red Team Operator | VAPT Addict ⚔️ Introduction: When Your AI Can Be Hacked With Words In an era where language models have become the co-pilots of our...
defending-code-reference-harness
Defending Code Reference Harness A reference implementation for autonomous vulnerability discovery and remediation with Claude, based on our learnings from partnering with security teams at several organizations since launching Claude Mythos Preview. For a write up of these learnings along with...
Anthropic-Credited-CVEs
ANTHROPIC CVE TRACKER Overview Tracking vulnerabilities that credit the Anthropic research team and are possibly discovered by Project Glasswing. CVEs: 501 GHSAs w/o CVE: 17 Advisories w/o GHSA/CVE: 120 Findings Withdrawn by Anthropic: 415 Distributions | ---|--- Anthropic Research Tracking CVEs...
MCP Inspector < 0.14.0 UnauthenticatedRemote Code Execution
The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to launch MCP commands over stdio. id...
vLLM <= 0.23.0 - Anthropic Router Heap Address Information Leak
vLLM = 0.23.0 incompletely fixes CVE-2026-22778. The original fix added sanitizemessage to the OpenAI router but the Anthropic-compatible router /v1/messages echoes strexc directly. id: CVE-2026-54236 info: name: vLLM = 0.23.0 - Anthropic Router Heap Address Information Leak author: kenlacroix...
cve-2025-65099
Proof of Concept for CVE-2025-65099 Further details are provided in the published article. yarnPath Technique A vulnerable environment for yarnPath can be initialized as follows: docker run --rm -v "$PWD":/poc -it --workdir /poc ubuntu bash -c 'apt-get update -qq && DEBIANFRONTEND=noninteractive...
CVE-2026-21852-PoC
Claude Code Vulnerability Educational Demo This project demonstrates three vulnerabilities disclosed by Check Point Research in Anthropic's Claude Code CLI tool. It is designed for cybersecurity students and researchers to understand how AI development tool supply-chain attacks work...
1shot (>=0.0.3, <=0.0.9), @4via6/relay (1.0.0) +256 more potentially affected by CVE-2026-88968 via @anthropic-ai/claude-code (>=0.2.14, <=2.1.240)
@anthropic-ai/claude-code NPM version =0.2.14, =0.0.3, =2.1.0, =0.1.18, =1.0.0, =0.4.0, =1.0.0, =0.2.3, =0.0.1, =0.0.55, =0.0.69 - @brandongtr/rule-agent-cli 1.0.1-beta.0 and more Source cves: CVE-2026-88968 Source advisory: GHSA-5XJX-9QX6-JCRV...
1shot (>=0.0.3, <=0.0.9), @4via6/relay (1.0.0) +256 more potentially affected by CVE-2026-88968 via @anthropic-ai/claude-code (>=0.2.14, <=2.1.240)
@anthropic-ai/claude-code NPM version =0.2.14, =0.0.3, =2.1.0, =0.1.18, =1.0.0, =0.4.0, =1.0.0, =0.2.3, =0.0.1, =0.0.55, =0.0.69 - @brandongtr/rule-agent-cli 1.0.1-beta.0 and more Source cves: CVE-2026-88968 Source advisory: OSV:GHSA-5XJX-9QX6-JCRV...
jf-langflow (>=1.10.0, <=1.10.0.post7), langflow (>=1.8.0rc0, <=1.8.0rc2) +20 more potentially affected by CVE-2026-97677 via lfx (>=1.10.0, <=1.12.0.dev10)
lfx PYPI version =1.10.0, =1.10.0, =1.8.0rc0, =0.10.0rc0, =1.12.0.dev10 - lfx-amazon 0.1.5 - lfx-anthropic 0.1.6 - lfx-arxiv 0.1.4 - lfx-bundles 1.1.19 - lfx-cohere 0.1.2 - lfx-datastax 0.1.7 - lfx-docling 0.1.5 - lfx-duckduckgo 0.1.4 - lfx-empiriolabs 0.1.2 - lfx-exa 0.1.2 - lfx-firecrawl 0.1.2 ...
@acampkin/mcc (>=2.1.0, <=2.5.0), @applydigital/claude (>=1.0.0, <=1.2.1) +32 more potentially affected by CVE-2026-88968 via @anthropic-ai/claude-code (>=2.0.32, <=2.1.240)
@anthropic-ai/claude-code NPM version =2.0.32, =2.1.0, =1.0.0, =0.0.1, =4.0.0, =0.7.5, =0.6.0-beta.1, =19.24.1, =1.0.0-broken, =0.0.1-rc.1, =0.0.1, =0.4.0, =1.0.0 and more Source cves: CVE-2026-88968 Source advisory: MEND:CVE-2026-88968...
@anthropic-ai/claude-code (>=2.1.116, <=2.1.250), @chude/memory (>=4.0.0, <=4.0.3) +9 more potentially affected by CVE-2026-88968 via @anthropic-ai/claude-code-darwin-x64 (>=2.1.116, <=2.1.250)
@anthropic-ai/claude-code-darwin-x64 NPM version =2.1.116, =2.1.116, =4.0.0, =0.8.0, =1.30.1-broken.0, =0.1.44-easy.50, =0.4.1, =2.1.207, =0.1.0, =2.8.0, =2.10.1 Source cves: CVE-2026-88968 Source advisory: MEND:CVE-2026-88968...
@anthropic-ai/claude-code (>=2.1.116, <=2.1.250), @chude/memory (>=4.0.0, <=4.0.3) +9 more potentially affected by CVE-2026-88968 via @anthropic-ai/claude-code-darwin-arm64 (>=2.1.116, <=2.1.250)
@anthropic-ai/claude-code-darwin-arm64 NPM version =2.1.116, =2.1.116, =4.0.0, =0.8.0, =1.30.1-broken.0, =0.1.44-easy.50, =0.4.1, =2.1.207, =0.1.0, =2.8.0, =2.10.1 Source cves: CVE-2026-88968 Source advisory: MEND:CVE-2026-88968...
Anthropic Claude Code race condition vulnerability
Versions of Anthropic Claude prior to 2.1.251 contain a security vulnerability. This vulnerability arises because the Edit tool fails to bind the underlying directory inode or file descriptor during pathname and symbolic link resolution validation. On macOS, code controlled by attackers within th...
A Supply Chain Attack Put Malicious Anthropic Claude Extensions on Thousands of Devices
Thanks to a lucky break, flawed code in a tainted Claude extension prevented the attacker from fully worming their way into some 5,000 developer machines...
Fake ChatGPT and Claude Apps Abuse Signed Executables to Deploy Crypto Miners
Threat actors are delivering malicious loaders and cryptocurrency miners under the guise of artificial intelligence AI desktop applications for Anthropic Claude and OpenAI ChatGPT as part of a campaign dubbed Yoba. The activity involves creating fake GitHub projects that claim to be desktop...
jf-langflow (>=1.10.0, <=1.10.0.post7), langflow (>=1.8.0rc0, <=1.8.0rc2) +21 more potentially affected by CVE-2026-93680 via lfx (>=1.10.0, <=1.13.0.dev47)
lfx PYPI version =1.10.0, =1.10.0, =1.8.0rc0, =0.10.0rc0, =0.1.4, =0.3.3.dev44, =0.3.3.dev47 and more Source cves: CVE-2026-93680 Source advisory: MEND:CVE-2026-93680...