Marius CiepluchandClaude Opus 5.5 6bfb05f952 spec(pre-push-safety-net): pre-register the hunter experiment on population v2 ...

This is the deciding experiment of the strategy review, fixed before any v2 pin is
hunted.
- Hunter: the unchanged tool hunter (default prompt, tools and 4 steps) on
  deepseek-flash.
- Scope: the ranker's top 20 regions for the case family, in four hunts. The model
  never sees the fix diff or the declared sites.
- Families: a fixed keyword table maps the model's family to the protocol's three.
- Scoring: exactly protocol v2's scorer.
- Cost: a hard $10 ceiling.

hunt.py runs it and scores it (--score). A pilot on a v1 development case
(mongo-express) found the vulnerability at lib/bson.js:60, at $0.031 per pin,
alongside a lot of speculative noise.

Transport fix found by the pilot: the DeepSeek endpoint the hunter builds was
unpriced, so the cost meter read $0.00 for any number of calls. It is now priced.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

2026-09-28 09:10:02 +02:00

..

fixtures

feat(three-stage-scan): gate stage-2 maps against split-sink ranking

2026-09-04 11:53:06 +02:00

independent

spec(pre-push-safety-net): pre-register the hunter experiment on population v2

2026-09-28 09:10:02 +02:00

manifests

feat(three-stage-scan): add aliased-sink mutation the regex scan misses

2026-09-04 11:50:44 +02:00

measurements

measure(sqli): PMPro 1-in-5 sample after the fifth fix -- 1/5, recall pins intact

2026-09-24 13:36:36 +02:00

pairs

feat(corpus): vendor 40 OWASP xss pairs as the owasp slice

2026-09-08 17:28:11 +02:00

push

perf(taint): ask the caller check only of a parameter that starts a flow into the field

2026-09-23 22:49:44 +02:00

ranking

feat(pre-push-safety-net): preserve uncertainty in benchmark scoring

2026-09-12 19:04:20 +02:00

repos

feat(pre-push-safety-net): pin labeled evaluation inputs

2026-09-12 18:45:54 +02:00