My LibraryCart 3

Benchmarks

Prompt-Injection Regression Corpus

Prompt-Injection Regression Corpus

31,00 €

Evaluate defensive prompt-injection handling with a versioned synthetic corpus and reproducible, documented test expectations.

Purchase terms

Your purchase includes the edition described on this page. Later releases are separate unless this offer explicitly includes an update entitlement.

Source checks and new-release publication do not change the historical coverage or automatically add future editions to an earlier purchase.

Edition details

Edition
zf-046-2026-1-e69535a560d5
Files
CHANGELOG.md, LICENSE.md, README.md, REFUND.md, SUPPORT.md, artifacts/changelog-CHANGELOG.md, artifacts/checksums-checksums.json, artifacts/data-dictionary-DATA-DICTIONARY.md, artifacts/full-full.csv, artifacts/full-full.jsonl, artifacts/full-full.parquet, artifacts/known-limitations-KNOWN-LIMITATIONS.md, artifacts/license-LICENSE.md, artifacts/manifest-manifest.json, artifacts/provenance-provenance.json, artifacts/quality-report-quality-report.json, artifacts/readme-README.md, artifacts/sample-sample.csv, artifacts/schema-schema.json, artifacts/source-policy-source-policy.json, checksums.json, cover.svg, download-manifest.json, gumroad-product.json, health-check.json, output-contract.json, quality-manifest.json, rollback.json, sample-data.json, smoke-fixture.json
Formats
CSV, JSON, JSONL, MD, PARQUET, SVG
Coverage
Immutable, clearly labelled synthetic benchmark cases for deterministic regression and release-gate evaluation.
Geographic scope
Immutable, clearly labelled synthetic benchmark cases for deterministic regression and release-gate evaluation.
Publisher
Zentra-authored synthetic benchmark cases
Source updated
Explicitly unknown; see immutable provenance for the recorded source retrieval.
Source checked
2026-07-14T18:22:43+02:00
Released
2026-07-14T18:22:43+02:00
Licence and attribution
# Marketplace licence Use is governed by the licence and terms shown on the canonical marketplace listing. Source provenance and third-party source rights remain attached to delivered artifacts. No custom or negotiated licence is implied.

Source basis: Zentra-authored synthetic benchmark cases (synthetic; no external source)

Schema

FieldTypeDescription
case_idstring
benchmarkstring
categorystring
titlestring
inputstring
expected_resultstring
severitystring
rationalestring
syntheticboolean

Sample preview

Open the public sample

benchmarkcase_idcategoryexpected_resultinputrationaleseveritysynthetictitle
Deterministic fixture Benchmark for Prompt-Injection Regression CorpusDeterministic fixture Case Id for Prompt-Injection Regression CorpusDeterministic fixture Category for Prompt-Injection Regression CorpusDeterministic fixture Expected Result for Prompt-Injection Regression CorpusDeterministic fixture Input for Prompt-Injection Regression CorpusDeterministic fixture Rationale for Prompt-Injection Regression CorpusDeterministic fixture Severity for Prompt-Injection Regression Corpus1Deterministic fixture Title for Prompt-Injection Regression Corpus
Deterministic fixture Benchmark for Prompt-Injection Regression Corpus 2Deterministic fixture Case Id for Prompt-Injection Regression Corpus 2Deterministic fixture Category for Prompt-Injection Regression Corpus 2Deterministic fixture Expected Result for Prompt-Injection Regression Corpus 2Deterministic fixture Input for Prompt-Injection Regression Corpus 2Deterministic fixture Rationale for Prompt-Injection Regression Corpus 2Deterministic fixture Severity for Prompt-Injection Regression Corpus 2Deterministic fixture Title for Prompt-Injection Regression Corpus 2
Deterministic fixture Benchmark for Prompt-Injection Regression Corpus 3Deterministic fixture Case Id for Prompt-Injection Regression Corpus 3Deterministic fixture Category for Prompt-Injection Regression Corpus 3Deterministic fixture Expected Result for Prompt-Injection Regression Corpus 3Deterministic fixture Input for Prompt-Injection Regression Corpus 3Deterministic fixture Rationale for Prompt-Injection Regression Corpus 3Deterministic fixture Severity for Prompt-Injection Regression Corpus 31Deterministic fixture Title for Prompt-Injection Regression Corpus 3
Deterministic fixture Benchmark for Prompt-Injection Regression Corpus 4Deterministic fixture Case Id for Prompt-Injection Regression Corpus 4Deterministic fixture Category for Prompt-Injection Regression Corpus 4Deterministic fixture Expected Result for Prompt-Injection Regression Corpus 4Deterministic fixture Input for Prompt-Injection Regression Corpus 4Deterministic fixture Rationale for Prompt-Injection Regression Corpus 4Deterministic fixture Severity for Prompt-Injection Regression Corpus 4Deterministic fixture Title for Prompt-Injection Regression Corpus 4
Deterministic fixture Benchmark for Prompt-Injection Regression Corpus 5Deterministic fixture Case Id for Prompt-Injection Regression Corpus 5Deterministic fixture Category for Prompt-Injection Regression Corpus 5Deterministic fixture Expected Result for Prompt-Injection Regression Corpus 5Deterministic fixture Input for Prompt-Injection Regression Corpus 5Deterministic fixture Rationale for Prompt-Injection Regression Corpus 5Deterministic fixture Severity for Prompt-Injection Regression Corpus 51Deterministic fixture Title for Prompt-Injection Regression Corpus 5
Category:

Use a fixed synthetic corpus to test how your own defensive workflow handles the prompt-injection cases actually included in the release. The package is designed for repeatable regression evaluation rather than changing a test set silently between runs.

What this download contains

The corpus is not proof of comprehensive injection resistance and does not establish the security of a production deployment. Case coverage, expected behaviour and version history define what a result can show. Evaluation should stay in an isolated environment without real external side effects.

Working with this edition

Inspect the case inventory and expected outcomes, connect the supported cases to your test harness and record the corpus version with every run. Compare defensive changes against the same baseline, and investigate failures rather than suppressing them to obtain a passing report.

Product questions

Does passing prove my agent is immune to prompt injection?

No. It demonstrates behaviour on the included synthetic cases, not every possible adversarial input or integration.

Can I compare different defensive implementations?

Use the same versioned cases and expected outcomes as a repeatable baseline, and record your own harness and configuration. A comparison is meaningful for the tested cases, not a universal security ranking.

Reviews

There are no reviews yet.

Be the first to review “Prompt-Injection Regression Corpus”

Your email address will not be published. Required fields are marked *

Related products