LAB PROTOCOL · SECRET-SURFACE SCORECARD

Agent Secret-Leakage Observability: Incident Reconstruction Without Exposure

A 15-scenario incident-reconstruction drill for measuring whether observability preserves useful evidence while preventing secrets from becoming durable logs, screenshots, transcripts, or delegated context.

Protocol brief · July 22, 2026 · Editorial lab-design note

Why this benchmark matters

The highest-risk secret exposure can be created while diagnosing a failure. Useful observability requires evidence minimization, redaction before persistence, and access controls across every retention surface.

Scope note: This protocol defines a test design, not a performance claim. Results depend on implementation, model configuration, permissions, tool behavior, and the test fixtures used.

Measurement matrix

Test surfaceWhat to observeEvidence-led assessment
Pre-log redactionTool arguments, headers, and environment-derived valuesVerify secret patterns are removed before a log event is serialized.
Error tracesFailures that echo requests or provider responsesCheck stack traces, retries, and debug bundles for raw credentials.
Visual evidenceScreenshots and screen recordingsConfirm sensitive fields are masked before capture and export.
Delegated contextSub-agent prompts and handoff summariesEnsure secrets are excluded from task context and retained summaries.
Retention controlsExports, transcripts, and incident artifactsMeasure expiry, access scope, deletion path, and auditability.

Protocol steps

  1. Seed 15 controlled synthetic secrets across tool inputs, failures, screenshots, transcripts, and handoff data.
  2. Trigger normal, retry, error, and incident-export flows without using any production credential.
  3. Inventory every persisted and user-visible surface, then test whether the synthetic value or a reversible derivative is present.
  4. Score redaction coverage, evidence usefulness, export controls, and time to remove an exposed artifact.
  5. Document gaps as surface-specific findings and retest after changes to logging, support tooling, or delegation policy.

Lab disclosure

This page was developed from a July 22, 2026 lab-bench brief supplied by the Content Site Consultant. It is a proposed evaluation protocol, not an independent benchmark result or product-security certification.