748 matches found
CVE-2026-100585
OpenClaw npm package "openclaw" before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission reques...
EUVD-2026-87466
OpenClaw npm package openclaw before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request...
CVE-2026-100585
The OpenClaw npm package (openclaw) versions prior to 2026.7.1 contains an authorization bypass vulnerability. The software fails to enforce an owner-only requirement for Claude Code permission prompts sent via the MCP channel bridge . This allows an authorized non-owner channel sender with comma...
CVE-2026-100585 OpenClaw before 2026.7.1 Authentication Bypass via MCP Channel
OpenClaw npm package openclaw before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request...
CVE-2026-100585 OpenClaw before 2026.7.1 Authentication Bypass via MCP Channel
OpenClaw npm package openclaw before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request...
CVE-2026-100585: Missing Authorization
OpenClaw npm package openclaw before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request...
LLM Agents Can Easily Tamper with Their Own Traces
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Cod...
ai.codriverlabs:scaleout-build-control-plane-api (0.0.1-centraltest), ai.codriverlabs:scaleout-build-ecs (0.0.1-centraltest) +11513 more potentially affected by CVE-2026-91777 via com.fasterxml.jackson.core:jackson-databind (>=2.22.0, <=2.22.2)
com.fasterxml.jackson.core:jackson-databind MAVEN version =2.22.0, =0.9.3, =0.9.4, =0.9.7, =0.8.0, =0.9.9, =0.9.6, =0.7.0, =0.9.3, =0.9.9, =0.7.0, =0.7.0, =0.9.8 and more Source cves: CVE-2026-91777 Source advisory: MEND:CVE-2026-91777...
claude-security-audit
Claude Security Audit A complete security auditor for Clau...
Exploit for Injection in Dkfz Nnu-Net
Agentic workflow injection: fixtures and a coverage comparison...
Using AI for Weapons Development
Last week, Anthropic released a long and detailed document describing current misuses of their Claude models. I'm still reading it, but I wanted to flag this: We identified a cell of threat actors based in northern Yemen running three weapons development programs: a guided rocket that used a...
sandbox-runtime v0.0.76
Anthropic Sandbox Runtime srt A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container. srt uses native OS sandboxing primitives sandbox-exec on macOS, bubblewrap on Linux and proxy-based network filterin...
When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents
Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also introduces security and privacy risks because malicious instructions from external sources may be written into persistent memory and persist across...
Seraphim
Seraphim Agentic AI security scanner that proves exploitabili...
raptor v3.1.0
╔═══════════════════════════════════════════════════════════════════════════╗ ║ ║ ║ ██████╗ █████╗ ██████╗ ████████╗ ██████╗ ██████╗ ║ ║ ██╔══██╗██╔══██╗██╔══██╗╚══██╔══╝██╔═══██╗██╔══██╗ ║ ║ ██████╔╝███████║██████╔╝ ██║ ██║ ██║██████╔╝ ║ ║ ██╔══██╗██╔══██║██╔═══╝ ██║ ██║ ██║██╔══██╗ ║ ║ ██║ ██║█...
CVE-2026-73222
creationtimestamp| type| source ---|---|--- 2026-09-03 20:35:04+00:00| published-proof-of-concept| https://github.com/davila7/claude-code-templates/security/advisories/GHSA-79wm-x847-7cvg...
GHSA-79WM-X847-7CVG Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)
Summary npx claude-code-templates --studio launches "Claude Code Studio", an Express HTTP server cli-tool/src/sandbox-server.js, default port 3444 that binds to all interfaces 0.0.0.0, sets Access-Control-Allow-Origin: , and requires no authentication. Two POST endpoints pass attacker-controlled...
NPM: Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)
NPM: Claude Code Templates: Unauthenticated OS command injection RCE in Claude Code Studio server --studio vulnerability discovered by ? in WordPress Npm claude-code-templates versions = 1.29.2...
Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)
Summary npx claude-code-templates --studio launches "Claude Code Studio", an Express HTTP server cli-tool/src/sandbox-server.js, default port 3444 that binds to all interfaces 0.0.0.0, sets Access-Control-Allow-Origin: , and requires no authentication. Two POST endpoints pass attacker-controlled...