Secrets adversary

Scans repository text for committed credentials and narrow credential exposure paths.

Goals

The adversary is designed to produce a small number of high-confidence, actionable findings grounded in concrete repository evidence. Its review should be deterministic where possible, explicit about impact, and quiet when the available evidence does not justify a finding.

Scope

It evaluates repository text and narrow code paths for committed credentials, private keys, tokens, connection strings, secret manifests, and credential exposure through errors.

The complete detector or review inventory is maintained in CHECKS.md.

SDK dependency

The SDK uses the immutable development Git revision recorded in package.json and package-lock.json; the exact commit is listed below. Replace this pin with the published npm patch version after SDK PR #71 is released. The SDK is licensed under Apache-2.0 and bundled into this adversary's runtime, so release reviews should account for that dependency license.

Boundaries

It stays within this domain, does not execute target code, and leaves unrelated concerns to the corresponding specialist adversaries.

SDK source coverage

The SDK dependency follows the published SDK version pinned in package.json. Model review retains evidence-backed findings when repository source coverage is partial, records the limitation, and does not grant a whole-change clean opinion. Provider and output-validation failures are not coverage gaps: they retain failure or model-unavailable reporting and cannot grant a whole-change clean opinion.

Bounded model output repair

Model stages use the SDK output-validation loop with at most two final-generation requests (initial output plus one repair), unless a stage already supplies its own bounded validator. Broker and client schema failures provide specific feedback to final generation; gathered evidence and the original deadline are retained. Rejected completion usage is included in returned totals and terminal or interrupted ModelReviewError failures. Unexpected exceptions from custom model implementations propagate unchanged and do not expose SDK usage totals; custom models should report request failures with ModelReviewError. Exhausted validation remains incomplete and cannot grant a whole-change clean opinion.

This release uses SDK 0.1.43, including schema repair and interrupted-repair usage preservation.

Provider transport retries and format corrections have their own existing bounds; the two-attempt limit applies to SDK final-generation requests.

SDK 0.1.43

This release rebuilds with SDK 0.1.43. SDK PR #73 adds a tested neutral fallback to formatOpinionAsync when concern wording validation is exhausted, preserving completed findings and the ship decision. Reviewers that do not call this API retain their existing opinion behavior. Provider and transport failures remain errors. Domain rules and evidence requirements are unchanged.