mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 03:35:09 +02:00
docs(security): document GSTACK_SECURITY_ENSEMBLE env var
Adds the opt-in DeBERTa-v3 ensemble to the Sidebar security stack section of CLAUDE.md. Documents: * What it does (L4c cross-model classifier, 2-of-3 agreement for BLOCK) * How to enable (GSTACK_SECURITY_ENSEMBLE=deberta) * The cost (721MB model download on first run) * Default behavior (disabled — 2-of-2 testsavant + transcript) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -236,7 +236,13 @@ always BLOCKs (deterministic).
|
|||||||
**Env knobs:**
|
**Env knobs:**
|
||||||
- `GSTACK_SECURITY_OFF=1` — emergency kill switch. Classifier stays off even if
|
- `GSTACK_SECURITY_OFF=1` — emergency kill switch. Classifier stays off even if
|
||||||
warmed. Canary is still injected; just the ML scan is skipped.
|
warmed. Canary is still injected; just the ML scan is skipped.
|
||||||
|
- `GSTACK_SECURITY_ENSEMBLE=deberta` — opt-in DeBERTa-v3 ensemble. Adds
|
||||||
|
ProtectAI DeBERTa-v3-base-injection-onnx as L4c classifier for cross-model
|
||||||
|
agreement. 721MB first-run download. With ensemble enabled, BLOCK requires
|
||||||
|
2-of-3 ML classifiers agreeing at >= WARN (testsavant, deberta, transcript).
|
||||||
|
Without ensemble (default), BLOCK requires testsavant + transcript at >= WARN.
|
||||||
- Classifier model cache: `~/.gstack/models/testsavant-small/` (112MB, first run only)
|
- Classifier model cache: `~/.gstack/models/testsavant-small/` (112MB, first run only)
|
||||||
|
plus `~/.gstack/models/deberta-v3-injection/` (721MB, only when ensemble enabled)
|
||||||
- Attack log: `~/.gstack/security/attempts.jsonl` (salted sha256 + domain only,
|
- Attack log: `~/.gstack/security/attempts.jsonl` (salted sha256 + domain only,
|
||||||
rotates at 10MB, 5 generations)
|
rotates at 10MB, 5 generations)
|
||||||
- Per-device salt: `~/.gstack/security/device-salt` (0600)
|
- Per-device salt: `~/.gstack/security/device-salt` (0600)
|
||||||
|
|||||||
Reference in New Issue
Block a user