Claude reconstructs own leaked source code

// 57d agoSECURITY INCIDENT

Claude reconstructs own leaked source code

On March 31, 2026, a production update for Anthropic's Claude Code accidentally included a 60MB sourcemap containing 512,000 lines of TypeScript, allowing the community to reconstruct its core logic. Developers successfully used Claude itself to navigate dependency resolution and rebuild a functional executable from the leaked fragments, effectively turning the tool into its own reverse-engineering agent.

// ANALYSIS

This incident provides a comprehensive architectural blueprint for high-performance agentic loops, potentially commoditizing Anthropic's unique state management and tool-calling strategies. The use of an LLM to autonomously decompile and "fix" its own leaked codebase demonstrates a new level of recursive utility, while the exposure of internal features and kill-switches like "tengu_miraculo_the_bard" underscores the difficulty in securing sophisticated agentic systems.

// TAGS

claude-codeanthropicsource-leakagentic-aireverse-engineeringopen-sourcecybersecurity

DISCOVERED

57d ago

2026-04-01

PUBLISHED

57d ago

2026-03-31

RELEVANCE

10/ 10

AUTHOR

ZvenAls

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS39m ago

Dev lets Claude trade BTC overnight, nets $95 profit

A developer gave Claude a $20 budget to autonomously script and execute Bitcoin trades overnight, waking up to a functional trading bot and a $95 profit across five trades.

OPEN SOURCE1h ago

Plannotator 0.19.24 adds Amp support and configurable storage

Plannotator 0.19.24 is a substantial release that expands the tool beyond Claude Code with native Amp support, adds a `PLANNOTATOR_DATA_DIR` override so users can move the default `~/.plannotator` data directory, introduces Auto Mode in the permission selector for newer Claude Code versions, and fixes a Pi approval crash after plan acceptance. The update folds multiple stacked PRs into one release and pushes the project further toward a multi-agent review layer rather than a single-agent hook utility.

UPDATE2h ago

Grok Build widens access, adds subagents

xAI’s Grok Build is an early-beta terminal coding agent with plan-review-approve flows, parallel subagents, worktree isolation, and support for plugins, hooks, skills, and MCP. The latest improvements make it feel less like a demo and more like xAI’s bid to compete seriously in the AI coding CLI race.