Data-Exfiltration

Grok Data Exfiltration via Cryptographic Context Injection

ATLAS OWASP CRITICAL ▲ 9.2 Ars Technica Security Aug 23, 2026

Researchers at Adversa have demonstrated a novel prompt injection bypass against Grok, xAI's LLM, in which malicious instructions are encrypted using PBKDF2 and AES-256-GCM before being embedded in attacker-controlled web content. Because Grok's safety filters inspect plaintext input and output but not the results of its own code execution, the decrypted instructions execute without warning, causing the model to exfiltrate the user's name, location, and chat history to an attacker-controlled server. The vulnerability was disclosed to xAI in June 2026 but remained unpatched at time of publication, underscoring the systemic difficulty of defending LLMs against prompt injection at the model level.

CVE-2026-24301: Microsoft Copilot One-Click Data Exfiltration

ATLAS OWASP HIGH ▲ 9.1 The Hacker News Aug 20, 2026

Varonis Threat Labs disclosed three vulnerabilities in Microsoft Copilot Personal, collectively named CoSnitch (CVE-2026-24301), that allow an attacker to silently exfiltrate data from connected services with a single crafted link. The attack exploits an undocumented autorun=1 URL parameter that Copilot itself revealed during adversarial meta-hacking interrogation, enabling automatic prompt execution inside the victim's authenticated session. A separate third vulnerability allows persistent memory poisoning via web page summarization, potentially shaping future Copilot sessions.

Anthropic Enables Claude Code Auto Mode by Default for Pro Users

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.8 TechCrunch AI Aug 10, 2026

Anthropic is enabling auto mode as the default for Claude Code on Pro, Max, and Team accounts starting August 14, allowing the agent to proceed autonomously unless an action is deemed irreversible, destructive, or out-of-scope. The move addresses a well-documented defender gap — human approval fatigue in agentic pipelines — backed by testing data showing auto mode caught 89% of harmful actions versus 13.6% under manual review. Residual maturity questions remain around enterprise-level customisation of hard deny rules, integration with existing security tooling, and auditability of autonomous decisions at scale.

Poison Claude Proxy Exposes All Customer Prompts to Operators

ATLAS OWASP HIGH ▲ 8.2 The Hacker News Aug 10, 2026

Researchers have uncovered underground services selling discounted access to Anthropic's Claude models by routing requests through fraudulent AWS Bedrock accounts, with operators gaining full visibility into every customer prompt. The services, including Poison Claude and Ecomagent.in, function as man-in-the-middle proxies that pass user queries to Anthropic while harvesting sensitive prompt data. With nearly 900 active users on Poison Claude alone, the privacy and data exfiltration risks are significant for developers and organisations unknowingly using these rogue API gateways.

Atlassian Rovo Prompt Injection Leaks Jira Data to Attackers

ATLAS OWASP HIGH ▲ 8.5 The Hacker News Aug 08, 2026

Two independent security firms discovered that Atlassian's Rovo AI assistant can be manipulated through indirect prompt injection to exfiltrate Jira and Confluence data to attacker-controlled servers. PromptArmor demonstrated a file-borne injection chain requiring no separate approval step, while Varonis uncovered a URL parameter flaw (RovoBlast) that preloads attacker instructions into Rovo Chat with a single authenticated click. The link-parameter vulnerability was patched server-side by Atlassian on July 8, 2026, but the content-borne injection path lacks a direct patch.

Meta Plans Billions of Personal AI Agents on WhatsApp

FIRST LOOK ATLAS OWASP HIGH ▲ 7.8 TechCrunch AI Jul 30, 2026

Meta CEO Mark Zuckerberg has publicly committed to deploying personal AI agents at billion-user scale within five years, with WhatsApp and Meta's messaging surfaces as the primary delivery channel for agents managing finances, health, relationships, and household tasks. This represents a massive expansion of agentic AI attack surface, as persistent, goal-directed agents operating 24/7 on behalf of individuals will hold unprecedented access to sensitive personal data and actionable context. Defenders must anticipate new classes of prompt injection, data exfiltration, and agent impersonation threats operating at a scale and intimacy that dwarfs current enterprise agentic deployments.

Perplexity Launches Personal Computer AI Agent for Windows PCs

FIRST LOOK ATLAS OWASP HIGH ▲ 8.2 The Verge AI Jul 29, 2026

Perplexity has expanded its Personal Computer agentic tool to Windows, enabling a locally-run AI agent that can access files, Office 365 apps, and the web on behalf of enterprise users. This significantly expands the attack surface for defenders: a compromised or manipulated agent running with local system access can exfiltrate files, execute unauthorised actions, and pivot across cloud-connected Microsoft 365 services. Security teams should treat this as a high-privilege process requiring the same scrutiny as endpoint detection tools, with particular attention to prompt injection via locally-processed documents.

Agentic AI Disrupts Confidential Computing Security Boundaries

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 Dark Reading Jul 23, 2026

Agentic AI systems are introducing new security challenges to confidential computing environments, threatening the trust boundaries that Trusted Execution Environments (TEEs) and secure enclaves were designed to enforce. Defenders must contend with the fact that agents operating inside or alongside confidential compute environments can exfiltrate data, accept malicious instructions, or undermine attestation guarantees in ways that existing controls were not designed to catch. Security teams deploying AI pipelines adjacent to sensitive data vaults need to reassess their threat models to account for agentic autonomy as a new attack surface.

Microsoft Copilot MCP Tool Poisoning Enables Data Exfiltration

ATLAS OWASP HIGH ▲ 9.1 The Hacker News Jul 04, 2026

Microsoft researchers have demonstrated how attackers can embed hidden instructions inside MCP tool descriptions to covertly redirect AI agents into exfiltrating sensitive business data. Because each individual action the agent takes appears legitimate — using approved tools and the user's own permissions — default security controls generate no alerts. The attack exploits a fundamental design tension in MCP: tool descriptions simultaneously carry operational instructions and attacker-controlled data, collapsing a critical trust boundary.

Google DeepMind Releases AI Agent Attack Taxonomy

FIRST LOOK ATLAS OWASP HIGH ▲ 8.7 SecurityWeek Jun 25, 2026

Google DeepMind researchers have released a structured taxonomy categorising adversarial attacks against autonomous AI agents into six classes — content injection, semantic manipulation, cognitive state poisoning, behavioural control, systemic, and human-in-the-loop traps — formalising an emerging threat model for agentic AI systems. For defenders, this framework codifies attack paths that exploit the agent's inability to distinguish trusted instructions from attacker-controlled data ingested from web pages, emails, documents, and tool outputs. NIST evaluation data cited in the research shows malicious instruction injection succeeded in 57% of tested agent hijacking scenarios on average, underscoring that these are active, high-yield attack vectors rather than theoretical concerns.

Bayer and Thoughtworks Ship PRINCE Agentic RAG Platform

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 HN AI Security Jun 22, 2026

Bayer AG and Thoughtworks have published a detailed case study on PRINCE, a production agentic RAG system combining multi-agent orchestration, Text-to-SQL, and human-in-the-loop workflows to answer complex pharmaceutical preclinical research questions and draft regulatory documents. The system's architecture — spanning intent clarification, planning, retrieval, reflection, and writing agents with access to decades of safety study data — introduces a broad attack surface including prompt injection across agent boundaries, SQL injection via natural language, and sensitive data exfiltration through compromised agent outputs. Defenders evaluating similar agentic platforms should treat each inter-agent handoff as a trust boundary requiring independent validation and focus on data leakage controls given the sensitivity of preclinical regulatory data.

GitHub Ships Data Analytics Agent Built on Copilot

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.8 GitHub Blog Jun 20, 2026

GitHub has published a detailed engineering account of how it built an internal data analytics agent using GitHub Copilot, exposing the architectural patterns — including natural language-to-SQL translation, autonomous tool invocation, and internal data access — that underpin such systems. For defenders, this blueprint highlights concrete risks around prompt injection into analytics pipelines, excessive agency over sensitive internal datasets, and the challenge of auditing LLM-generated queries before execution. Organisations adopting similar agentic analytics patterns should treat this as a reference threat model rather than a safe-to-copy architecture.

Google Launches Android 17 with Gemini Omni Integration

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 TechCrunch AI Jun 17, 2026

Android 17 embeds Gemini Omni, AudioLM, and Lyria 3 directly into core OS functions including call handling, video editing, real-time audio translation, and emergency detection on Pixel devices. This deep integration gives defenders on-device AI capabilities that can surface anomalous behaviour, support safer communications, and automate emergency response without requiring third-party tooling. Organisations adopting Android 17 in managed fleets should establish baseline permission policies and input-validation standards to ensure these capabilities mature into enterprise-grade controls.

OpenClaw Agent Vulnerable to Prompt Injection RCE

ATLAS OWASP HIGH ▲ 8.5 The Hacker News Jun 12, 2026

Two independent research teams demonstrated that OpenClaw, a self-hosted AI agent, is vulnerable to prompt injection attacks delivered through shared contacts, vCards, location pins, and plain emails — enabling attacker-controlled code execution and sensitive data exfiltration. Imperva's finding, now patched in version 2026.4.23, exploited the agent's failure to mark message objects as untrusted before passing them to the underlying LLM. Varonis separately showed that a single crafted email could instruct an agent to forward mock AWS credentials and customer data to an external address, a behaviour-level risk no patch can fully remediate.

OpenClaw AI Agent Vulnerable to Phishing, Leaks AWS Credentials

ATLAS OWASP HIGH ▲ 8.5 BleepingComputer Jun 10, 2026

Varonis Threat Labs demonstrated that the OpenClaw open-source AI agent framework is vulnerable to social engineering attacks analogous to those used against human targets, successfully tricking the agent into exfiltrating AWS credentials, database secrets, and CRM exports to attacker-controlled addresses. The research tested two LLMs (Gemini 3.1 Pro and GPT-5.4) across generic and phishing-aware configurations, finding that even the hardened profile did not fully prevent data leakage. These findings highlight that autonomous AI agents with broad tool access and insufficient identity verification represent a significant and largely unaddressed attack surface in enterprise environments.

Data-Exfiltration

Stay ahead of the threat.