Agentic fuzz-testing of sandbox platforms: point a coding agent at your own hosted sandbox environment and let it try to break it
A platform engineer simulates real customers by wrapping the platform in an MCP server, releasing a coding agent against it, and having the agent generate and execute 1,000 test workflows across 10 domains. Results go into a SQLite database (not markdown files) so multiple sub-agents can run concurrently and failures can be queried. Failures are then classified into interface-layer bugs (issues in the MCP/encoding layer) versus sandbox-layer limits (memory, file permissions, persistence, seccomp, eBPF), because sandbox constraints decide whether an agent can finish its task at all.
online B2B Deep Tech / Infrastructure
From AI Engineer — 1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS at 00:20
Problem: Agent workloads are arbitrary and varied, so their demands on a sandbox environment diverge greatly from a classic long-running REST API service; sharp edges in sandbox primitives (filesystem permissions, mounted filesystems, persistence vs ephemerality, process spawning, memory) surface only when agents actually run diverse workflows, and are innocuous to human-written tests.
For: Engineering teams building or hosting agent platforms and sandboxed execution environments (code interpreters, cloud browsers) for agent workloads.
Products from this video
Examples
- The author's own run against Amazon Bedrock AgentCore: image uploaded and downloaded came back different due to incorrect encoding at the MCP layer; a null byte derailed tests; files written to a sandbox directory were not retrievable.
Other takes on AI security infrastructure
- Agentic consent governance layer for autonomous AI systems
- Enterprise agentic last-mile identity and access control layer
- Identity-based security infrastructure for multi-agent AI systems
- AI-agent security and control infrastructure for enterprises
- A guardrail tool that enforces strict test-driven development and other engineering rules for AI coding agents
- Privacy-first document preprocessing layer for AI coding agents