#DataExfiltration

@cybermaterial.bsky.social

5 days ago

Chrome Extension Goes Rogue After Sale
Read More: buff.ly/UarSEmh

#ChromeExtension #QuickLens #ShotBird #MaliciousUpdate #BrowserSecurity #SupplyChainRisk #DataExfiltration #InfosecAlert

0 0 0 0

The Daily Tech Feed

@thedailytechfeed.com

1 week ago

Cybercriminals are now exploiting Microsoft's AzCopy to stealthily exfiltrate data in ransomware attacks. Learn how to protect your organization from this emerging threat. #CyberSecurity #Ransomware #DataExfiltration Link: thedailytechfeed.com/ransomware-o...

0 0 0 0

CyberMaterial

@cybermaterial.bsky.social

1 week ago

ClawJacked Flaw Exposes OpenClaw Users
Read More: buff.ly/bTWMCMG

#ClawJacked #OpenClaw #AIAgentSecurity #LocalAgentRisk #DataExfiltration #VulnerabilityAlert #PatchNow #DevSecurity

0 0 0 0

CyberMaterial

@cybermaterial.bsky.social

2 weeks ago

Air Côte d'Ivoire Confirms Cyberattack
Read More: buff.ly/UqO4Kwl

#AirCoteDIvoire #INCRansomware #AviationCyber #DataExfiltration #RansomwareAttack #CriticalInfrastructure #IncidentResponse #GlobalCyber

0 0 0 0

TechNadu

@technadu.com

2 weeks ago

APT28 Deploys Macro Malware in Browser-Based Exfiltration Operation Targeting Europe The APT28 threat group used webhook-based macro malware in Operation MacroMaze to exfiltrate data from European entities.

Full breakdown:
www.technadu.com/apt28-deploy...

Do you think organizations are adequately monitoring outbound traffic to legitimate cloud services? Comment your opinion below.
#CyberEspionage #APT28 #CyberSecurity #MacroMalware #ThreatIntelligence #DataExfiltration

0 0 0 0

CyberTaters

@potato.software

2 weeks ago

Clawdbot, now OpenClaw, runs locally and can take real action on a user’s machine.

API keys, OAuth tokens, and chat histories stored in plaintext. Predictable file paths. Exposed control panels.

Read more:
www.blackfog.com/clawdbot-and...

#AI #DataExfiltration #PotatoSecurity

0 0 0 0

BlackFog

@blackfog.com

2 weeks ago

ClawdBot and OpenClaw: When Local AI Becomes A Data Exfiltration Goldmine | BlackFog ClawdBot stores API keys, chat histories, and user data in plaintext, and infostealers like RedLine, Lumma, and Vidar are already targeting it.

Clawdbot, now OpenClaw, runs locally and can take real action on a user’s machine.

API keys, OAuth tokens, and chat histories stored in plaintext. Predictable file paths. Exposed control panels.

Read more:
www.blackfog.com/clawdbot-and...

#AI #DataExfiltration #CyberSecurity

0 0 0 0

CyberMaterial

@cybermaterial.bsky.social

3 weeks ago

Hackers Stole 2 Quadrillion Bytes
Read Now: buff.ly/yZVvjhE

#IsraelCyber #CyberWarfare #DataExfiltration #NationStateThreat #GlobalCyber #ThreatAssessment #CriticalInfrastructure #InfosecNews

0 0 0 0

it business

@itbusiness-schweiz.bsky.social

3 weeks ago

Threat Report: Datenexfiltration stark gestiegen – «it business» – Meldungen aus der ICT-Welt

Der Arctic Wolf Threat Report 2026 zeigt eine klare Verschiebung: Datenexfiltration ohne Verschlüsselung nimmt deutlich zu. #ArcticWolf #ThreatReport #Cybersecurity #Ransomware #DataExfiltration #ITSecurity #ThreatIntelligence #Cyberresilienz

0 0 0 0

Winbuzzer

@winbuzzer.com

3 weeks ago

OpenAI Launches ChatGPT Lockdown Mode for High-Risk Users OpenAI has introduced ChatGPT Lockdown Mode, a security setting that restricts web browsing and disables advanced features to protect high-risk users.

winbuzzer.com/2026/02/18/o...

OpenAI Launches ChatGPT Lockdown Mode for High-Risk Users

#AI #ChatGPT #OpenAI #AISecurity #PromptInjection #DataExfiltration

0 0 0 0

CyberMaterial

@cybermaterial.bsky.social

1 month ago

Russian Ransomware Hackers Hit Tulsa Airport
Read More: buff.ly/glnBbUM

#QilinRansomware #AirportSecurity #CriticalInfrastructure #RansomwareAttack #DataExfiltration #AviationCyber #CyberIncident #ThreatIntel

0 0 0 0

Manuel Bissey

@mbissey.bsky.social

1 month ago

Mandiant Finds ShinyHunters-Style Vishing Attacks Stealing MFA to Breach SaaS Platforms Mandiant reports ShinyHunters-linked vishing attacks abusing MFA and SSO to breach SaaS apps, steal data, and extort organizations.

ShinyHunters is abusing trusted cloud services to exfiltrate data — blending in to stay invisible. When legit platforms are weaponized, detection must focus on behavior. ☁️🕵️‍♂️ #ThreatActors #DataExfiltration

0 0 0 0

BlackFog

@blackfog.com

1 month ago

Why Exfiltration of Data is the Biggest Cyberthreat Facing Your Business | BlackFog What do firms need to know about exfiltration of data in order to keep their operations secure?

If your security focus is perimeter first, you’re missing the real threat. Data exfiltration has eclipsed other attack vectors and drives today’s biggest breaches.

www.blackfog.com/why-exfiltra...

#CyberSecurity #DataExfiltration #Ransomware #Infosec #DataProtection #RiskManagement

1 0 0 0

CyberMaterial

@cybermaterial.bsky.social

1 month ago

Gemini Prompt Flaw Exposed Calendar Data
Read More: buff.ly/42IasCs

#GoogleGemini #PromptInjection #AIsecurity #CalendarData #IndirectPrompting #DataExfiltration #CyberResearch #Infosec #AIThreats

0 0 0 0

BlackFog

@blackfog.com

1 month ago

How MCP Could Become a Covert Channel for Data Theft | BlackFog Find out how Model Context Protocol (MCP) could be abused as a covert channel for data theft: five real risks, examples, and mitigations.

Could the Model Context Protocol (MCP) become a covert channel for data theft? New analysis shows attackers could abuse MCP connections to siphon sensitive context and exfiltrate data outside traditional controls.

www.blackfog.com/mcp-could-be...

#AIsecurity #MCP #DataExfiltration #Cybersecurity

1 1 1 0

Winbuzzer

@winbuzzer.com

1 month ago

Security Flaw Resurfaces in Anthropic’s New Claude Cowork Tool Days After Launch - WinBuzzer Anthropic has launched Cowork with a known data exfiltration vulnerability that researchers reported in October 2025 but remained unpatched for the January 13 release.

winbuzzer.com/2026/01/17/s...

Security Flaw Resurfaces in Anthropic’s New Claude Cowork Tool Days After Launch

#AI #Anthropic #Claude #CyberSecurity #AISecurity #AIAgents #ClaudeCowork #PromptInjection #DataExfiltration #AIRisks #AITools #FilesAPI #AgenticAI #PromptArmor

1 0 0 0

CySecurity News

@cysecuritynews.bsky.social

1 month ago

Security Researchers Warn of ‘Reprompt’ Flaw That Turns AI Assistants Into Silent Data Leaks Cybersecurity researchers have revealed a newly identified attack technique that shows how artificial intelligence chatbots can be manipulated to leak sensitive information with minimal user involvement. The method, known as Reprompt, demonstrates how attackers could extract data from AI assistants such as Microsoft Copilot through a single click on a legitimate-looking link, while bypassing standard enterprise security protections. According to researchers, the attack requires no malicious software, plugins, or continued interaction. Once a user clicks the link, the attacker can retain control of the chatbot session even if the chat window is closed, allowing information to be quietly transmitted without the user’s awareness. The issue was disclosed responsibly, and Microsoft has since addressed the vulnerability. The company confirmed that enterprise users of Microsoft 365 Copilot are not affected. At a technical level, Reprompt relies on a chain of design weaknesses. Attackers first embed instructions into a Copilot web link using a standard query parameter. These instructions are crafted to bypass safeguards that are designed to prevent direct data exposure by exploiting the fact that certain protections apply only to the initial request. From there, the attacker can trigger a continuous exchange between Copilot and an external server, enabling hidden and ongoing data extraction. In a realistic scenario, a target might receive an email containing what appears to be a legitimate Copilot link. Clicking it would cause Copilot to execute instructions embedded in the URL. The attacker could then repeatedly issue follow-up commands remotely, prompting the chatbot to summarize recently accessed files, infer personal details, or reveal contextual information. Because these later instructions are delivered dynamically, it becomes difficult to determine what data is being accessed by examining the original prompt alone. Researchers note that this effectively turns Copilot into an invisible channel for data exfiltration, without requiring user-entered prompts, extensions, or system connectors. The underlying issue reflects a broader limitation in large language models: their inability to reliably distinguish between trusted user instructions and commands embedded in untrusted data, enabling indirect prompt injection attacks. The Reprompt disclosure coincides with the identification of multiple other techniques targeting AI-powered tools. Some attacks exploit chatbot connections to third-party applications, enabling zero-interaction data leaks or long-term persistence by injecting instructions into AI memory. Others abuse confirmation prompts, turning human oversight mechanisms into attack vectors, particularly in development environments. Researchers have also shown how hidden instructions can be planted in shared documents, calendar invites, or emails to extract corporate data, and how AI browsers can be manipulated to bypass built-in prompt injection defenses. Beyond software, hardware-level risks have been identified, where attackers with server access may infer sensitive information by observing timing patterns in machine learning accelerators. Additional findings include abuses of trusted AI communication protocols to drain computing resources, trigger hidden tool actions, or inject persistent behavior, as well as spreadsheet-based attacks that generate unsafe formulas capable of exporting user data. In some cases, attackers could manipulate AI development platforms to alter spending controls or leak access credentials, enabling stealthy financial abuse. Taken together, the research underlines that prompt injection remains a persistent and evolving risk. Experts recommend layered security defenses, limiting AI privileges, and restricting access to sensitive systems. Users are also advised to avoid clicking unsolicited AI-related links and to be cautious about sharing personal or confidential information in chatbot conversations. As AI systems gain broader access to corporate data and greater autonomy, researchers warn that the potential impact of a single vulnerability increases substantially, underscoring the need for careful deployment, continuous monitoring, and ongoing security research.

Security Researchers Warn of ‘Reprompt’ Flaw That Turns AI Assistants Into Silent Data Leaks #ArtificialIntelligence #CyberSecurity #DataExfiltration

1 1 0 0

CyberMaterial

@cybermaterial.bsky.social

1 month ago

Reprompt Attack Steals Microsoft Copilot Data
Read More: buff.ly/AHYG9Id

#MicrosoftCopilot #PromptInjection #LLMSecurity #AIAppSec #GenAISecurity #PromptHacking #DataExfiltration #CyberResearch #SecurityWeek #Varonis

0 0 0 0

TechNadu

@technadu.com

1 month ago

Anthropic Claude Vulnerability Exposes Cowork AI to Data Exfiltration via Prompt Injection A critical Anthropic Claude vulnerability in Cowork AI allows data exfiltration via prompt injection, as the AI interprets malicious data as executable instructions.

Full Article: www.technadu.com/anthropic-cl...

Do you think current AI guardrails are enough? Comment your opinion.
#AIsecurity #PromptInjection #Anthropic #LLMs #CyberRisk #DataExfiltration #EnterpriseSecurity

0 0 0 0

Ars Technica News

@arstechni.ca

2 months ago

A single click mounted a covert, multistage attack against Copilot https://arstechni.ca #dataexfiltration #promptinjections #Security #copilot #Biz&IT #LLMs #AI

1 0 0 0

CyberMaterial

@cybermaterial.bsky.social

2 months ago

Chrome Extensions Steal AI Chats
Read More: buff.ly/N6kVLLC

#MaliciousExtensions #ChromeSecurity #AIPrivacy #ChatGPTSecurity #DeepSeek #BrowserThreats #DataExfiltration #SupplyChainRisk

0 0 0 0

Ars Technica News

@arstechni.ca

2 months ago

ChatGPT falls to new data-pilfering attack as a vicious cycle in AI continues https://arstechni.ca #dataexfiltration #promptinjections #Security #chatbots #Biz&IT #AI

0 0 0 0

The Daily Tech Feed

@thedailytechfeed.com

2 months ago

Cybercriminals are exploiting PuTTY for stealthy lateral movement and data exfiltration. Learn how to detect and mitigate these threats. #CyberSecurity #PuTTY #DataExfiltration Link: thedailytechfeed.com/cybercrimina...

0 0 0 0

ThreatInsight

@threatinsight.proofpoint.com

2 months ago

Redirection to adding authorized device.

New research from Proofpoint ‼️

Threat actors are using #phishing tactics to trick users into giving access to #M365 accounts.

⚠️ Successful compromise leads to #accounttakeover, #dataexfiltration, and more.

Blog: brnw.ch/21wYtcM

Here’s what you need to know. 🧵⤵️

2 2 1 1

DysruptionHub

@dysruptionhub.infosec.exchange.ap.brid.gy

2 months ago

Pit River Health Service cyber incident disrupts records access in California Pit River Health Service in California says a cyber incident disrupted EHR and Dentrix access; some data was copied as systems are restored.

Pit River Health Service cyber incident disrupts records access in California #PitRiverHealthService #CybersecurityIncident #ElectronicHealthRecords #Dentrix #DataExfiltration #California dysruptionhub.com/pit-river-health-cyber-i...

0 0 0 0

DysruptionHub

@dysruptionhub.infosec.exchange.ap.brid.gy

3 months ago

We have seen no evidence that sensitive data was accessed Organizations often reassure the public with phrases like "no evidence data was accessed." This explains why those statements reveal so little.

When a company suffers a cyberattack, there is one line you can almost set your watch by: "At this time, we have seen no evidence that sensitive data was accessed" #Ransomware #DataExfiltration #Transparency dysruptionhub.com/no-evidence-sensitive-da...

0 0 0 0

BlackFog

@blackfog.com

3 months ago

5 Ways Large Language Models (LLMs) Enable Data Exfiltration | BlackFog Explore how LLMs enable data exfiltration through prompt injection, RAG abuse, memory leaks, tool misuse and fine-tuning.

LLMs boost productivity — but also open new paths for data exfiltration.

Top 5 risks:
1️⃣ Prompt injection
2️⃣ RAG abuse
3️⃣ Memory leaks
4️⃣ Agent/tool misuse
5️⃣ Fine-tuning data exposure

🔗 Read more in our latest blog: www.blackfog.com/5-ways-llms-...

#CyberSecurity #AI #LLM #DataExfiltration

1 0 0 0

BlackFog

@blackfog.com

3 months ago

Cybersecurity in 2026 : Expert Prediction – Global Security Mag Online Cybersecurity in 2026 : Expert Prediction

Cyber experts share the first predictions for 2026.
• Shadow AI = #1 threat
• AI makes data exfiltration precise
• Shadow AI drives breach costs
• SIEM replaced by prevention + AI
🔗 globalsecuritymag.com/cybersecurity-in-2026-expert-prediction.html

#CyberSecurity #ShadowAI #DataExfiltration