Session
AI Agent (and MCP) Vulnerabilities and Security
While everyone discusses building AI Agents, few discuss the security risks involved.
In fact, MCP is a security nightmare currently.
Like any other IT application, AI Agents' security is also important, and we will deep dive into this.
In addition to prompt injection and jailbreaking, I will focus on attack vectors in the MCP, including:
- Command injection
- Tool poisoning via manipulated tool descriptions/metadata
- Privilege escalation through chained tool access
- Persistent context
- Shadowing tool descriptions in MCP registries
This would be a fun session, which will also make you think.
Nikhilesh Tayal
Google Developer Expert for AI. Co-founder - "AI ML etc." (an educational platform for Senior IT professionals to learn AI). Instructor at LinkedIn Learning. 70+ speaking assignments.
Udaipur, India
Links
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top