mlsanityData to 14 Oct 2026

Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound

arXiv 2609.05920 ↗First posted 5 Sep 2026cs.CR cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Agent Skills combine instructions with files, packages, tools, models, and services, so operational identity can exceed a signed directory. Recursive or lazy dependencies may change while root-level evidence remains valid, and different surfaces may reach the same durable effect. We present ClosureBound, a reference monitor that prevents authorization transfer across material changes to this heterogeneous closure. Its resolver commits typed graph nodes and topology. Each grant binds an exact closure root, effect ceiling, purpose/provenance, validity, and epochs. At durability, it re-resolves closure and state, normalizes the operation into an external-effect IR, and admits it only if a joint witness satisfies every bound. Supported equivalent paths share one ceiling. Assuming complete mediation and discovery, authenticated freshness, sound normalization, cryptographic binding, and authoritative linearization, we establish metadata non-authority, closure determinism, version non-inheritance, effect non-amplification, bound-value freshness, and path invariance. We do not establish program equivalence or remote-service honesty. A provider-free implementation matches 40 frozen lifecycle fixtures; 18 kernel contracts and six mutants cover binding and downgrade cases. Full-profile exploration reaches 84,608 states and 530,752 transitions without a declared invariant violation; six weakened profiles yield witnesses. A lexical audit of 549 public Skills (4,872 unique files) finds that 21 of 526 roots with bundled files name every non-manifest path verbatim, 67 contain links resolving outside their roots, and no root declares a frontmatter dependencies field. These observations motivate conservative closure discovery and define concrete targets for broader runtime, interoperability, efficacy, and production validation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 56 references that are in the map. First posted on arXiv 5 Sep 2026.

Builds on

27 of 56 references.

References · 27

  1. 2026Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scalecited by 105
  2. 2024Cedar: A New Language for Expressive, Fast, Safe, and Analyzable Authorization (Extended Version)cited by 34
  3. 2026Formal Policy Enforcement for Real-World Agentic Systemscited by 33
  4. 2026Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflowscited by 30
  5. 2026BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoningcited by 27
  6. 2026Formal Analysis and Supply Chain Security for Agentic AI Skillscited by 25
  7. 2026MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skillscited by 19
  8. 2026Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agentscited by 18
  9. 2026AIRGuard: Guarding Agent Actions with Runtime Authority Controlcited by 13
  10. 2026Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystemscited by 13
  11. 2026Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registrycited by 12
  12. 2026AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skillscited by 12
15 more
  1. 2026Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malwarecited by 10
  2. 2026VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skillscited by 9
  3. 2026Governing Dynamic Capabilities: Cryptographic Binding and Reproducibility Verification for AI Agent Tool Usecited by 8
  4. 2026Exploiting LLM Agent Supply Chains via Payload-less Skillscited by 6
  5. 2026SkillGuard: A Permission-Centric Framework for Agent Skill Securitycited by 6
  6. 2026SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skillscited by 5
  7. 2026Intent-Governed Tool Authorization for AI Agentscited by 5
  8. 2026Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluationcited by 5
  9. 2026OpenPort Protocol: A Security Governance Specification for AI Agent Tool Accesscited by 4
  10. 2026Sealing the Audit-Runtime Gap for LLM Skillscited by 3
  11. 2026Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Securitycited by 3
  12. 2026Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chainscited by 3
  13. 2026Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationalescited by 2
  14. 2026SIGIL: Compiling Agent Skills into Typed Harnessescited by 1
  15. 2026Auto-Policy, not Auto-Skill: Compiled Agent Skills for the Physical Worldcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.