FRAMEWORK / SECURITY

MLSecOps & Agentic Security

The Institute's security programme spans the MLSecOps Top 10 for the machine-learning lifecycle, collaboration with the Linux Foundation and OpenSSF on ML security practice, and active review of OWASP guidance for agentic systems. Machine-learning security remains relevant when the system starts calling tools.

01 — THE MLSECOPS TOP 10

The MLSecOps Top 10

MLSecOps is the application of security practices across the machine-learning lifecycle, connecting risks in data, model artifacts, pipelines, deployment and monitoring to practical controls. The Top 10 maps common machine-learning security failures to controls that teams can apply across those workflows, with code and worked examples maintained in the open-source fml-security repository.

OWASP vulnerabilityMLSecOps equivalent
Broken access controlUnrestricted model endpoints
Cryptographic failuresAccess to model artifacts
InjectionArtifact exploit injection
Insecure designInsecure ML systems and pipeline design
Security misconfigurationsData and ML infrastructure misconfigurations
Vulnerable and outdated componentsSupply-chain vulnerabilities in ML code
Identification and authentication failuresIAM and RBAC failures for ML services
Software and data integrity failuresML infrastructure, ETL and CI/CD integrity failures
Logging and monitoring failuresObservability, reproducibility and lineage failures
Server-side request forgeryML server-side request forgery

02 — THE AGENTIC FRONTIER

The agentic frontier

The MLSecOps taxonomy covers the lifecycle around models. Agentic systems add delegated authority, tools and memory to the attack surface. The OWASP Top 10 for Agentic Applications names these risks through the ASI taxonomy, and the Institute's founder is an official reviewer of it, named in the published documents; until those reviewer-credit documents are linked directly, see the OWASP announcement. The selected mappings below position these risks against principle-led controls without reproducing the full OWASP list.

Selected OWASP ASI categoryPrinciple and control framing
ASI01 · Agent Goal HijackConstrain mandates, separate external content from instructions, and gate consequential actions under P01 and P09.
ASI03 · Identity & Privilege AbuseGive each agent a distinct identity, least-privilege credentials and fail-closed policy gateways.
ASI04 · Agentic Supply Chain VulnerabilitiesVerify models, tools and dependencies, record provenance and restrict which components agents may load.
ASI06 · Memory & Context PoisoningDerive memory scope from authenticated identity, separate tenants and retain provenance for stored context.
ASI08 · Cascading FailuresBound delegation, cap retries and cost, expose action traces and contain failure at each agent boundary.

03 — BUILT WITH THE FIELD

Built with the field

04 — PRINCIPLE ANCHOR

Principle anchor

This programme implements P08 Safety by Security. Agent mandates and alignment risks also connect it to P01 Human Augmentation by Oversight and P09 Human Alignment by Intent.