PromptArmor — Cyber Attacks, Breaches & Threat Activity

Related Threat Clusters

• ChatGPT for Google Sheets Plugin Exposes Serious Data Exfiltration Risks

  A cybersecurity report from PromptArmor has revealed significant vulnerabilities in the 'ChatGPT for Google Sheets' plugin, which has over 185,000 downloads. The vulnerabilities stem from an indirect prompt injection…

  2 articles · Updated June 1, 2026
• Claude Cowork Vulnerable to File Exfiltration via Prompt Injection

  Anthropic's Cowork productivity AI is vulnerable to file exfiltration attacks due to unresolved prompt injection issues. The vulnerability allows attackers to exploit isolation flaws in Claude's code execution…

  3 articles · Updated January 15, 2026
• Google Patches GeminiJack Zero-Click Exploit in Gemini Enterprise

  Google has addressed a zero-click vulnerability in Gemini Enterprise and Vertex AI, identified as 'GeminiJack.' Discovered by Noma Labs in June 2025, this exploit could have allowed attackers to steal sensitive…

  4 articles · Updated December 10, 2025
• IBM's AI Agent Bob Compromised by Malware Execution

  IBM's AI coding agent, Bob, has been shown to be vulnerable to executing malware due to its failure to adhere to security standards. Currently in closed beta testing, Bob is designed to assist developers by…

  3 articles · Updated January 7, 2026

Recent Intelligence Reports

• Financial Data Crisis! ChatGPT Spreadsheet Plugin Exposes Serious Security Vulnerability — News.Aibase · June 1, 2026
• ChatGPT for Google Sheets Exfiltrates Workbooks — News.Ycombinator · May 31, 2026
• Anthropic's Files API exfiltration risk resurfaces in Cowork — Theregister · January 16, 2026
• Contagious Claude Code bug Anthropic ignored promptly spreads to Cowork — Theregister · January 15, 2026
• IBM's AI agent Bob easily duped to run malware, researchers show — Theregister · January 7, 2026
• Phantom Prompts and the Anti-Gravity Exploit: How Google Gemini Can Be Manipulated to ... — Webpronews · November 26, 2025

Related Entities