arXiv CS
open access
Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed
AI agents now install packages, call model APIs with their operators' keys and change code in repositories that deploy to production. The network, credentials and write access they need are also how they can leak data, steal a key or change a system nobody approved. Sandboxes contain an agent but le
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed#1489528
- EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence#1354993
- ADF-EA: A Unified Execution Assurance System for Agent Device Foundation#1105250
- ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents#405550
- Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills#971811
Record · ID 1483102
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive