[Pyhroff]

💡 What: Added a fast pre-check (_ROT13_KW.search(stripped)) before running multi-word regex parsing and _score_view decoding iterations for rot13 obfuscation detection in aisec/poison.py.

🎯 Why: Benign tool descriptions previously triggered expensive regex extraction (re.findall) and sentence scoring for rot13 candidates even when no rot13 keywords were present.

📊 Impact: ~7x speedup for views() execution on benign tool descriptions (~1.46s -> ~0.21s per 1000 iterations).

🔬 Measurement: Verified with python3 -m timeit benchmarking views(text) on benign tool descriptions, and verified zero regressions across unit tests (pytest).

---

PR created automatically by Jules for task 16988745444880007208 started by @Pyhroff

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.