TopicPublic Ready
Agent Security
Security of AI systems that retrieve, invoke tools, authorize actions, and create external consequences.
July 20, 2026Open
Start with the pressure: sales, launch, abuse, agents, data, or guardrails
Intelligence
Research pathways connecting findings, figures, statistics, publications, and source systems.
Security of AI systems that retrieve, invoke tools, authorize actions, and create external consequences.
Adversarial testing of realistic AI failure paths, authority boundaries, control failures, and external consequences.
The engineering discipline responsible for mapping, attacking, defending, and evidencing the security of AI products and systems.
Reproducible evidence that AI security controls exist, operate, and continue to work.
Governance language, control ownership, operating accountability, and defensible security claims for AI systems.
The research, building, security, governance, incident, staffing, and funding systems through which a discipline becomes real.
Hiring, role architecture, skills, seniority, labor supply, and workforce infrastructure for AI Security Engineering.
Security of the models, data, prompts, policies, tools, orchestration, infrastructure, and generated artifacts that compose AI products.
Vulnerability disclosures, exploited records, weakness patterns, and affected AI product surfaces.
Security of model artifacts, training and evaluation data, retrieval sources, embeddings, and model promotion workflows.
Public repository activity, security tooling, OpenSSF controls, and builder behavior across AI security ecosystems.
Security of retrieval-augmented generation systems, including authorization, poisoned context, retrieval abuse, and data exposure.