Incidents tagged Prompt Injection

Evidence indicates that Kiro is affected by a security issue. Reported affected versions include 0.7.45.

Fortinet Buys Virtue AI to Hunt Vulnerabilities in AI Agents Before Hackers Do Startup Fortune

Qualys TotalAI addresses the critical AI governance evidence gap by providing a unified platform to discover and continuously assess AI risks and vulnerabilities across the AI lifecycle. It enables organizations to generate audit-ready proof of AI control effectiveness, meeting escalating regulatory demands and mitigating threats like prompt injection and data leaks.

AI is significantly accelerating the attack lifecycle, compressing response windows, and increasing data breach costs, necessitating a shift from human-paced to machine-paced cybersecurity strategies. New vulnerabilities arise from attacks on AI models (e.g., inversion, prompt injection) and inadequately secured non-human identities, demanding robust AI access controls and comprehensive environmental security.

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis The Hacker News

This Copilot vulnerability could expose emails, 2FA codes, and other sensitive data Mashable

A critical zero-click vulnerability, dubbed "EchoLeak" and identified as CVE-2025-32711, was discovered in Microsoft Copilot. This flaw leveraged an "LLM scope violation" to allow remote attackers to exfiltrate sensitive data from Microsoft 365 services without any user interaction.

Claude Code RCE: claude-cli:// Deeplink Vulnerability Allows Arbitrary Command Execution (Patch 2.1.118) Pasquale Pillitteri

A critical vulnerability in Anthropic's Claude Code allows for the bypass of its permission system's deny rules. This flaw can be exploited via AI-generated prompt injection, enabling attackers to exfiltrate sensitive credentials and compromise cloud or CI/CD environments.

Autonomous AI trading agents in 2026 were compromised by protocol-level vulnerabilities such as memory poisoning and indirect prompt injection, targeting their long-term memory and execution protocols like the Model Context Protocol (MCP). These flaws facilitated over $45 million in crypto security breaches, including a $40 million drain from Step Finance amplified by excessive agent permissions.

The article outlines a comprehensive AI security roadmap addressing unique threats to LLMs and AI agents, such as prompt injection, data poisoning, model inversion, and data leakage, which exploit probabilistic system behaviors across the full AI lifecycle. It emphasizes applying frameworks like OWASP Top 10 for LLMs and NIST AI RMF to build defenses from data collection and training to deployment and runtime monitoring, mitigating these advanced vulnerabilities.

Three critical vulnerabilities (CVE-2026-34070, CVE-2025-68664, CVE-2025-67644) have been discovered in LangChain and LangGraph, widely used AI frameworks for building LLM applications. These flaws include path traversal, deserialization of untrusted data, and SQL injection, allowing attackers to access arbitrary filesystem files, leak environment secrets, and execute arbitrary SQL queries against conversation history databases.

The OWASP Top 10 for LLM Applications (2025) highlights critical security risks, notably Prompt Injection, where crafted inputs manipulate LLM behavior to bypass safeguards or achieve unauthorized access. Another key concern is Sensitive Information Disclosure, where LLMs can inadvertently leak confidential data, leading to privacy violations and intellectual property infringement.

Architectural vulnerabilities within Large Language Model (LLM) environments integrated with the Model Context Protocol (MCP) enable attackers to embed malicious instructions within data content or tool metadata. This flaw allows for indirect prompt injection and tool poisoning, compelling LLMs to autonomously perform unauthorized actions such as data exfiltration or triggering enterprise workflows.

LLM applications face significant security risks, primarily prompt injection attacks, where malicious inputs manipulate models into ignoring instructions and revealing sensitive data. This can lead to the exposure of internal configuration data, confidential information, or unauthorized actions within connected enterprise systems.

The RoguePilot vulnerability in GitHub Codespaces leveraged passive prompt injection within GitHub issues to manipulate Copilot. This enabled attackers to silently execute malicious commands and exfiltrate sensitive data, specifically the `GITHUB_TOKEN`, to external servers.

The OpenClaw open-source AI agent project rapidly exposed at least three high-risk Remote Code Execution (RCE) vulnerabilities, allowing attackers to perform high-authority tasks like shell command execution. These critical flaws are exacerbated by direct/indirect prompt injection, configuration errors, and supply chain poisoning through malicious plug-ins within its architecture.

The OpenClaw AI agent is critically vulnerable to remote code execution and extensive data exfiltration due to an authentication bypass where misconfigured reverse proxies improperly trust external requests as local. Additionally, the agent is susceptible to prompt injection attacks, enabling the extraction of private keys and sensitive user data from the underlying system.

Security researchers have identified a vulnerability where prompt injection attacks in LLM-powered applications can weaponize URL preview features to silently exfiltrate sensitive data. Attackers can craft malicious prompts that cause the LLM to generate URLs containing extracted confidential information, which is then transmitted to an attacker-controlled server when the application automatically fetches the URL preview.

OpenClaw, a rapidly adopted AI assistant with broad system access, presents significant security risks due to widespread deployment of internet-exposed instances by users. Threat actors are actively exploiting these misconfigurations, conducting prompt injection attempts and direct attacks via the WebSocket API for authentication bypasses and raw command execution.