Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore the emerging security threats posed by AI coding assistants in this conference talk that reveals how these helpful tools can become attack vectors. Discover real vulnerabilities found in Cursor, including arbitrary code execution and data exfiltration scenarios where attackers can compromise developers using nothing more than hidden text within codebases. Learn about the invisible attack vectors unique to agentic AI systems, where malicious prompts can silently influence behavior and spread through codebases like supply chain infections. Understand how prompt-jacking represents a new category of security risk in AI-assisted development environments. Gain practical defensive strategies that developers and organizations can implement immediately to protect against these novel attack methods and secure their AI-enhanced development workflows.
