DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.
What changed: Command injection and safety checks reorganized into modular architecture Impact: Same security coverage with better performance and maintainability - no change in user-facing behavior, but more accurate detection with fewer false positives
