CCopperSunDevinbrasscoders.hashnode.dev·15h ago · 5 min readWhat AI Coding Agents Leave Behind in ProductionEvery AI coding assistant produces two kinds of output: the code that solves the problem, and the scaffolding accumulated while solving it. Debug print statements that dump request objects to stdout. 00
CCopperSunDevinbrasscoders.hashnode.dev·15h ago · 6 min readYour README Is an Attack Surface for AI AgentsPull a third-party Python package into your project. Your AI coding assistant reads its README as context while it works. The README contains a line that looks like a maintainer note but is structured00
CCopperSunDevinbrasscoders.hashnode.dev·15h ago · 5 min readPydantic v2 Validation Bugs AI Assistants WriteAI assistants trained predominantly on pre-2023 Python code have a Pydantic problem. The v2 release shipped in June 2023 with a rewritten validator core — different execution order, different coercion00
CCopperSunDevinbrasscoders.hashnode.dev·15h ago · 6 min readOWASP Agentic Top 10 for Python DevelopersThe OWASP Top 10 for LLM Applications was written for a world where a user sends a prompt and reads the response. When the model starts taking actions — reading your filesystem, writing Python, callin00
CCopperSunDevinbrasscoders.hashnode.dev·15h ago · 5 min readMCP Tool Poisoning: What Static Scanners MissThe Model Context Protocol hands AI coding agents a list of tools — each with a name, a description, and an inputSchema. Before invoking any tool, the model reads its description. An attacker who cont00