nguiasoren/ROGUE red-team gate

Red-team your LLM deployment on every PR and fail on any HIGH/CRITICAL breach.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
endpointOpenAI-compatible base URL of your deployment (e.g. https://gateway.acme.com/v1). Use this OR provider+model.no""
providerKnown provider when not using a custom endpoint: openai / anthropic / openrouter / gemini / groq.no""
modelTarget model id. Required in provider mode; optional for an endpoint (uses the endpoint default).no""
system-promptInline system prompt of your deployment — red-team your REAL config, not a bare model.no""
system-prompt-filePath (in the consumer repo) to a file holding the system prompt. Alternative to system-prompt.no""
packBundled attack pack: aggressive / default / compliance.noaggressive
max-testsCap on the number of attacks run.no50
judgeGrader: 'keyless' (heuristic, default, no key) or 'calibrated' (LLM judge — requires judge-key).nokeyless
budgetOptional USD cost cap; the scan stops after this much target-call spend.no""
api-keyCredential for the TARGET endpoint/provider. Pass via a repo secret.no""
judge-keyCredential for the calibrated judge (only used when judge: calibrated). Pass via a repo secret.no""
fail-onMinimum breached-finding severity that fails the PR: high (default) | critical | medium | low | none.nohigh
max-breach-rateOptional float 0-1; also fail when the overall breach rate exceeds it (e.g. 0.2 = 20%).no""
baselinePath to a committed baseline snapshot JSON; fail the PR if a family regressed vs it (a re-opened / worsened bypass).no""
max-regressionAllowed per-family breach-rate increase (0-1) before it fails the gate (default 0.0 = any re-opened bypass fails).no0.0
baseline-savePath to write THIS scan's baseline snapshot (run on main to record the golden state, then commit it).no""
python-versionPython used to install and run the gate.no3.11
card-dirDirectory the breach-card artifact is written to.norogue-scan
namedescription
breachesNumber of breached findings.
breach-rateOverall breach rate (0-1).
failed'true' if the gate failed, else 'false'.
regressed'true' if a family regressed vs the baseline, else 'false'.
cardPath to the breach-card artifact (PNG, or SVG fallback).