ZitPit: Consumer-Side Admission Control for Agentic Software Intake
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
AI IDEs and coding agents compress discovery, fetch, workspace open, installation, and execution into one low-observability loop. Existing defenses such as provenance frameworks, package and repository firewalls, runtime protection, and tool-approval prompts each cover part of that path, but they often leave the final consumer-side execution decision implicit. ZitPit is a 100% open-source Rust system that argues for a stricter boundary: first-seen external artifacts should become durable policy events before they gain execution rights on protected developer or CI hosts. The current public evidence is intentionally narrow and explicit. It includes repeated Git smart-HTTP intake measurements showing that approved artifacts can remain faster than unmanaged public fetch, plus implemented protected-session and governed-egress proof families. The broader contribution is architectural rather than universal-coverage-by-assertion: ZitPit unifies artifact admission, repo-open state, capability-scoped execution, and durable policy records at the consumer execution boundary for agentic workflows.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 0 of its 28 references that are in the map. First posted on arXiv 5 Apr 2026.
Builds on
0 of 28 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps
- 2026Zero2Repo: Can Coding Agents Build Repositories from Scratch?
- 2026Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents
- 2026OpenComputer: Verifiable Software Worlds for Computer-Use Agents
- 2026Towards a Benchmark for Dependency Decision-Making
- 2026ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
- 2026RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue
- 2026PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents