Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
A protocol driven framework is presented that binds SBOM and AIBOM artefacts to deterministic environment capture and structured runtime telemetry. Exploitability is computed from declared artefacts, observed activation conditions, and enforced execution policies. CSAF VEX advisories are generated from combined static and runtime evidence, cryptographically signed, and validated through deterministic replay. Evaluation uses approximately 10000 component entries across synthetic Agentic AI workloads 50 to 5000 components, incorporating OSV, GitHub Advisory, KEV, and EPSS datasets.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 2 of its 59 references that are in the map. First posted on arXiv 16 Jun 2026.
Builds on
2 of 59 references.
References · 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry
- 2026AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems
- 2026POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation
- 2026Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations
- 2026SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation
- 2025AgentSight: System-Level Observability for AI Agents Using eBPF
- 2026AgentTrace: A Structured Logging Framework for Agent System Observability
- 2025Verifiability-First Agents: Provable Observability and Lightweight Audit Agents for Controlling Autonomous LLM Systems