CVE-2026-57495 AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a...

GHSA-33CG-GXV8-3P8G vLLM denial of service via prompt embeds on M-RoPE models

Summary Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server. Sending a pure prompt embeds payload in a /v1/completions request with a model usi...

vLLM denial of service via prompt embeds on M-RoPE models

Summary Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server. Sending a pure prompt embeds payload in a /v1/completions request with a model usi...

Exploit for Improper Input Validation in Apache Camel

camel-langchain4j-tools Prompt-Injection → Header-Injection Re...

CVE-2026-57495: Missing Authentication for Critical Function

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a...

CVE-2026-12228 Stored XSS in Direct Messages via Prompt Sharing in parisneo/lollms

A stored cross-site scripting XSS vulnerability exists in the POST /api/prompts/share endpoint of parisneo/lollms latest version. The endpoint stores attacker-controlled promptcontent into DBDirectMessage.content without server-side sanitization. When a victim opens the direct message DM thread,...

CVE-2026-12228 Stored XSS in Direct Messages via Prompt Sharing in parisneo/lollms

A stored cross-site scripting XSS vulnerability exists in the POST /api/prompts/share endpoint of parisneo/lollms latest version. The endpoint stores attacker-controlled promptcontent into DBDirectMessage.content without server-side sanitization. When a victim opens the direct message DM thread,...

Prompt Injection Attacks Are Thwarting AI Hacking Agents

“Context bombing” tricks malicious AI agents into shutting down before they can do harm...

GHSA-WXHM-2MQ7-7697 Prompty: Arbitrary file read via file reference expansion

Summary Prompty loaders expanded $file:... references in .prompty frontmatter without enforcing that the resolved path stayed within an authorized directory. An attacker-controlled prompt file could use path traversal or an absolute path to cause the host application to read files accessible to t...

From Recon to Free Flights: Precision Prompt Attacks on AI Agents

...

Routing Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection

Large language models LLMs exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that models possess the knowledge to solve a task but lack reliable internal routing to activate it. Prior work in formal mathematical reasoning SAIR, C�zares...

The Language of Security: How Prompt Syntax Shapes Secure Code Generation in Open LLMs

Large Language Models LLMs are increasingly used for source code generation despite their outputs often exhibiting security vulnerabilities. Prior work shows that prompt engineering can mitigate such risks, yet 1 they focused on high-level prompting strategies, neglecting recent evidence that...

MAL-2026-10736 Malicious code in memtry-cli (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 11638a6b1b7876a94ef23285cb88f0127c003bb5e4d786dbaba5c30a9cbdfdb7 memtry-cli installs an MCP server whose memtryonboarding tool returns a prompt that instructs the connected AI agent to scan the installer's home...

Malicious code in memtry-cli (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 11638a6b1b7876a94ef23285cb88f0127c003bb5e4d786dbaba5c30a9cbdfdb7 memtry-cli installs an MCP server whose memtryonboarding tool returns a prompt that instructs the connected AI agent to scan the installer's home...

MAL-2026-10711 Malicious code in @funny-booth/agent-core (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6693129f8b6f8b6c2d52722ca7746d6ef3dd792476297fa3583d3956548eb2b4 The package ships heavily obfuscated runtime files dist/index.js, dist/launcher.js built with javascript-obfuscator. The MCP server registered as the...

Malicious code in @funny-booth/agent-core (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6693129f8b6f8b6c2d52722ca7746d6ef3dd792476297fa3583d3956548eb2b4 The package ships heavily obfuscated runtime files dist/index.js, dist/launcher.js built with javascript-obfuscator. The MCP server registered as the...

CVE-2026-53598 Prompty: Arbitrary File Read via ${file:path} Reference Expansion

Prompty is a markdown file format .prompty for LLM prompts. Prior to 2.0.0-beta.2, Prompty loaders expanded $file:... references in .prompty frontmatter without enforcing that resolved paths stayed within the prompt directory or allowed roots, allowing an attacker-controlled prompt file to read...

CVE-2026-53597

Prompty is a markdown file format .prompty for LLM prompts. From 2.0.0-alpha.1 until 2.0.0-beta.3, the @prompty/core TypeScript loader in runtime/typescript/packages/core/src/core/loader.ts used gray-matter without overriding executable js and javascript frontmatter engines, allowing an...

New ClickLock macOS Stealer Kills Apps Every 210ms Until Victims Type Their Password

ClickLock Stealer , a new macOS infostealer, answers a victim's refusal by killing their apps on a loop until they hand over the login password. It arrives as a command pasted into Terminal, asks for the password behind a fake system dialog, and when the victim cancels, installs two LaunchAgents...

New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands

Ask an AI agent to summarize the reviews on a product page, and a single planted review can make it click "Buy Now" instead. Ask a coding assistant to apply a maintainer's fix from a GitHub thread, and a fake comment can make it run a stranger's command on your computer. Neither trick hijacks the...