2 min lesson
Tool use & command execution abuse
Work through this: "You're designing file-write guardrails so the agent can only touch the workspace. A junior engineer ships a check that rejects any path containing '../'. What's wrong and what's the correct approach?"
Step 1 of 3
Every tool you hand the agent is a capability an attacker can borrow. A web-fetch tool is an exfil channel. A shell tool is arbitrary code execution. File-write is persistence. The security work is deciding what to grant, how narrowly and under what gate.
The JD calls this out directly: build the framework for securely handling agent manipulation of user systems - tool use, MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. Press Enter for the full definition., command execution, file writes. This section is where that responsibility lives and an onsite build round may ask you to sketch it.