Apoorv Mehta
Manager, Product Security @ ServiceNow
San Jose, California, United States
Actions
Apoorv Mehta is a Product Security Engineering Manager working at the intersection of AI, security, and large-scale enterprise platforms. He focuses on evaluating AI systems for production readiness, risk, and operational resilience, with an emphasis on identifying security, misuse, and governance gaps before deployment.
In his role, Apoorv regularly reviews AI architectures, workflows, and integrations to assess whether systems are safe to scale beyond proof-of-concepts. His work spans threat modeling for AI-driven features, access and trust boundary analysis, and the design of monitoring and control mechanisms for AI systems operating in production environments.
Apoorv brings a practitioner’s perspective to AI operations, grounded in real-world decision-making rather than theoretical models or tool-specific approaches. He is particularly interested in helping engineering teams and leaders develop consistent evaluation frameworks for approving AI systems responsibly and sustainably.
Links
Area of Expertise
Topics
Past the Lethal Trifecta: A Reachability-First Threat Model for Agentic AI
Almost every production AI agent today has Simon Willison's "lethal trifecta": access to private data, exposure to untrusted content, and a channel to communicate externally. Naming the trifecta is step one. It does not tell you which of your fifty agents to fix first, and most agentic-AI security talks stop exactly there — necessary framing, not a triage method.
This talk applies a reachability-first lens, the same discipline that turns an unusable pile of SAST and dependency-CVE findings into an actual priority list, to agentic AI. The trifecta tells you an agent is structurally vulnerable. Reachability tells you whether the vulnerable path is actually exposed to an attacker today: which tools an agent can reach, which of those tools touch untrusted content, and how far a compromised step can travel before something stops it.
The method has been independently pressure-tested across technical review sessions with senior security practitioners at multiple organizations, surfacing real gaps: MCP-specific tool poisoning, rug-pull updates that change a trusted tool's behavior after the fact, memory and context poisoning across sessions, and tool shadowing that impersonates a legitimate integration.
You leave with a way to rank your own agents by actual exploitability instead of trifecta-presence alone, and a short list of the MCP-specific attack patterns most threat models still miss.
Format: Talk, 20-25 minutes, Intermediate level.
Audience: AppSec, product security, and AI/ML security practitioners
building or securing agentic systems and MCP integrations.
No special AV or technical requirements.
BSides Bloomington 2026 Sessionize Event
BSides Orlando 2026 Sessionize Event
Apoorv Mehta
Manager, Product Security @ ServiceNow
San Jose, California, United States
Links
Actions
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