mlsanityData to 14 Oct 2026

Please Don't Kill My Vibe: Empowering Agents with Data Flow Control

arXiv 2512.05374 ↗First posted 5 Dec 2025cs.CR cs.AI cs.DBcited by 4

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

The promise of Large Language Model (LLM) agents is to perform complex, stateful tasks. This promise is stunted by significant risks - policy violations, process corruption, and security flaws - that stem from the lack of visibility and mechanisms to manage undesirable data flows produced by agent actions. Today, agent workflows are responsible for enforcing these policies in ad hoc ways. Just as data validation and access controls shifted from the application to the DBMS, freeing application developers from these concerns, we argue that systems should support Data Flow Controls (DFCs) and enforce DFC policies natively. This paper describes early work developing a portable instance of DFC for DBMSes and outlines a broader research agenda toward DFC for agent ecosystems.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 5 of its 30 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

5 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Design Patterns for Securing LLM Agents against Prompt Injections10 Jun

Other references · 4

  1. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  2. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  3. 2024Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architecturescited by 12
  4. 2025The Free Termination Property of Queries Over Timecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Designing for Doubt: The Case for Informed Abstention in Autonomous Agentscited by 3
  2. 2026PrismaDV: Automated Task-Aware Data Unit Test Generationcited by 1
  3. 2026Agentic Data Environmentscited by 0
  4. 2026Environment Steering: Using Data Flow Control to Improve Agent Utility and Safetycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems
  2. 2025FlowAgent: Achieving Compliance and Flexibility for Workflow Agents
  3. 2026Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
  4. 2026Towards Verifiably Safe Tool Use for LLM Agents
  5. 2026The LLMbda Calculus: AI Agents, Conversations, and Information Flow
  6. 2026Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
  7. 2026LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment
  8. 2026Characterizing Large Language Model Agentic Workflows: A Study on N8n Ecosystem