EUVD-2026-16602

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

BIT-DISCOURSE-2026-27740 Discourse has Stored XSS in AI Triage Automation

Discourse is an open-source discussion platform. Versions prior to 2026.3.0, 2026.2.1, and 2026.1.2 have a cross-site scripting vulnerability that arises because the system trusts the raw output from an AI Large Language Model LLM and renders it using htmlSafe in the Review Queue interface withou...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

nanobot 安全漏洞

Nanobot is a lightweight personal AI assistant open-source by Data Intelligence Lab@HKU. Versions of Nanobot prior to 0.1.6 contained a security vulnerability. This vulnerability stemmed from an indirect prompt injection issue in the email channel processing module, which could allow remote...

CVE-2026-30304

AI Code’s CVE-2026-30304 stems from its design that auto-executes commands deemed safe while requiring approval for potentially destructive ones. Multiple trusted sources describe a prompt-injection flaw: an attacker can wrap malicious commands in a generic template and fool the model into classi...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

PT-2026-28397

Name of the Vulnerable Software and Affected Versions AI Code affected versions not specified Description The software’s design, which includes options for executing safe and all commands, is susceptible to prompt injection attacks. The system is intended to automatically execute commands deemed...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

PT-2026-28507

Name of the Vulnerable Software and Affected Versions nanobot versions prior to 0.1.6 Description An indirect prompt injection exists in the email channel processing module nanobot/channels/email.py. This allows a remote, unauthenticated attacker to execute arbitrary Large Language Model LLM...

AI Code 安全漏洞

AI Code is a code programming assistant developed by TianGuaDuiZhang. AI Code has a security vulnerability, which stems from the design of automatic terminal command execution, making it susceptible to prompt injection attacks, potentially allowing arbitrary command execution...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

CVE-2026-32622

SQLBot is an intelligent data query system based on a large language model and RAG. Versions 1.5.0 and below contain a Stored Prompt Injection vulnerability that chains three flaws: a missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology,...

CVE-2026-32247

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Large Language Models LLMs have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented...

SUSE CVE-2026-30856

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...

CVE-2026-33060

CKAN MCP Server is a tool for querying CKAN open data portals. Versions prior to 0.4.85 provide tools including ckanpackagesearch and sparqlquery that accept a baseurl parameter, making HTTP requests to arbitrary endpoints without restriction. A CKAN portal client has no legitimate reason to...

CVE-2026-32622

SQLBot is an intelligent data query system based on a large language model and RAG. Versions 1.5.0 and below contain a Stored Prompt Injection vulnerability that chains three flaws: a missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology,...

CVE-2026-27740

Discourse is an open-source discussion platform. Versions prior to 2026.3.0-latest.1, 2026.2.1, and 2026.1.2 have a cross-site scripting vulnerability that arises because the system trusts the raw output from an AI Large Language Model LLM and renders it using htmlSafe in the Review Queue interfa...

CVE-2026-27740

Discourse (open-source discussion platform) is affected by CVE-2026-27740. Versions prior to 2026.3.0-latest.1, 2026.2.1, and 2026.1.2 are vulnerable to stored XSS caused by trusting raw output from an AI Large Language Model and rendering it with htmlSafe in the Review Queue without adequate san...