FEATURES

Attack simulation for LLM apps and the web around them.

Guardrails and firewalls block attacks — DoesItDefend proves whether yours actually hold, with reproducible findings and checksum-verified evidence.

AI + web attack coverage

Run OWASP LLM Top 10 against your AI endpoints and OWASP Web Top 10 against the apps around them — one platform, one evidence trail.

See the coverage view

See the actual attack

Every finding ships the real evidence: the HTTP request that broke a web app, or the prompt-and-response that bypassed an AI guardrail.

Open a sample run

Validated remediation

For AI findings we generate a system-prompt patch and a guardrail config — then replay the attack to confirm the fix actually closes the bypass.

How remediation works

Eligible Starter+ runs include a checksum-verified evidence pack: SHA-256 hashes, a trace_id chain, and a run summary. LLM runs with eligible findings can also include conversation transcripts and a remediation playbook.

What is in a pack

Calibrated and reproducible

Probes come from a version-locked corpus, not improvised per run. An authorized reviewer can replay an observed finding from the persisted artifacts available to that run.

The calibration method

Detection-as-code export

One-click Sigma rule per finding so your SIEM gets a starter detection the moment the engine flags a gap. No engineering ticket.

See an example

CLI + GitHub Action gate

Block PRs that regress your LLM defenses. didk_ API keys + `doesitdefend scan` + diff-aware probe selection — quality gate that fits the dev loop.

Read the CI guide

Compliance evidence in one click

Findings auto-derive frameworks they constitute evidence for — EU AI Act, NIST AI RMF, SOC 2, ISO 27001, PCI-DSS, HIPAA, LGPD/GDPR. Eligible Starter+ evidence packs include per-framework SARIF.

See the mapping