5452 matches found
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...
CVE-2026-30304
The AI Code programming assistant, developed by TianGuaDuiZhang , is vulnerable to prompt injection attacks due to its automatic terminal command execution design. The system distinguishes between "safe" and "destructive" commands, automatically executing the former while requiring user approval ...
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-2026-33654: Improper Control of Generation of Code
nanobot is a personal AI assistant. Prior to version 0.1.6, an indirect prompt injection vulnerability exists in the email channel processing module nanobot/channels/email.py, allowing a remote, unauthenticated attacker to execute arbitrary LLM instructions and subsequently, system tools without...
Incorrect Authorization
Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization via the ACP permission resolution process. An attacker can bypass security prompting by providing conflicting tool identity hints in rawInput and metadata, which c...
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-2026-32897
OpenClaw versions prior to 2026.2.22 reuse gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay is set to hash and commands.ownerDisplaySecret is unset, creating dual-use of authentication secrets across security domains. Attackers with access to...
CVE-2026-3587
An unauthenticated remote attacker can exploit a hidden function in the CLI prompt to escape the restricted interface, leading to full compromise of the device...
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...
CVE-2026-33068
Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...
CVE-2026-31854
Cursor is a code editor built for programming with AI. Prior to 2.0 ,if a visited website contains maliciously crafted instructions, the model may attempt to follow them in order to “assist” the user. When combined with a bypass of the command whitelist mechanism, such indirect prompt injections...
The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
System prompt configuration can make the difference between near-total phishing blindness and near-perfect detection in LLM email agents. We present PhishNChips, a study of 11 models under 10 prompt strategies, showing that prompt-model interaction is a first-order security variable: a single...
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...
Leveraging Large Language Models for Trustworthiness Assessment of Web Applications
The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem as existing techniques primarily focus on detecting known...
SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy
Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation RAG, and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we m...
We Found Eight Attack Vectors Inside AWS Bedrock. Here's What Attackers Can Do with Them
AWS Bedrock is Amazon's platform for building AI-powered applications. It gives developers access to foundation models and the tools to connect those models directly to enterprise data and systems. That connectivity is what makes it powerful – but it’s also what makes Bedrock a target. When an AI...
EUVD-2026-14385
An unauthenticated remote attacker can exploit a hidden function in the CLI prompt to escape the restricted interface and gain root access to the underlying Linux based OS, leading to full compromise of the device...
