Deterministic SAST
Semgrep runs first: reproducible, auditable, with stable rule IDs you can pin and diff across runs. The same code yields the same findings — every time.
Model-agnostic · Cloudflare-native · SARIF 2.1.0
A model-agnostic AI harness that scans code for vulnerabilities.
Deterministic SAST meets evidence-based AI triage — reproducible coverage, model-agnostic adapter, confidence grounded in evidence.
- BYO-key · envelope-encrypted · shredded
- Code treated as data
- Immutable audit log
The pipeline — an auditable scan, end to end. Hover any stage for details.
The hybrid story
Deterministic floor, intelligent ceiling
Scanners give you reproducibility and stable rule IDs. The model gives you context and clarity. Neither is trusted blindly.
AI triage as a layer, not an oracle
The model adds context, deduplicates, writes plain-language explanations, and suppresses false positives. It fills a strict JSON schema only — code is passed as data, never as instructions.
Evidence-based confidence
Confidence is computed from evidence, not the model's self-rating: Semgrep ∩ LLM-confirmed = high; multi-model agreement raises it; LLM-only is labeled needs review.
Auditable output
Every scan emits SARIF 2.1.0 plus an immutable audit log — model id, version, prompt hash, ruleset versions — so results are reproducible and defensible.
BYO key is envelope-encrypted, used only for the scan, then shredded. Your code is never stored beyond the job's TTL and never used for training.
Live demo
Scan code right now
This calls the real API — no key required. Load the planted-vulnerability sample, hit run, and watch the harness catch it live in the terminal.
Public repos only. The worker fetches source files via the GitHub REST API (no token) and feeds them into the same pipeline.
Use your own Anthropic API key (optional)
Optional. If provided, your key is envelope-encrypted, used only for this scan, then shredded. Your code is never stored beyond the job or used for training.
aiharness@cf:~$
Findings
Download SARIFStandards & best practices
Mapped to the frameworks your auditors already use
Every reference links to its authoritative source. We align on technical merit.
Weakness taxonomy
Application risk
Findings format
Secure SDLC
AI governance
Supply chain
Organizational security
- ISO/IEC 27001 (ref)
- SOC 2 (ref)
- NIST CSF 2.0
Critical infrastructure / OT
Code quality
Executive Order 14110 was revoked in Jan 2025 — we align to SSDF / AI-RMF on technical merit, not the executive order.
Standards marked (ref) — ISO/IEC 27001, ISO/IEC 42001, and SOC 2 — are references and alignment targets, not certifications held.
Use cases
Where teams deploy AIHarness
CI / PR gate
Block merges over a severity threshold and post SARIF straight to the pull request. Deterministic rule IDs keep the gate stable across runs.
Pre-acquisition code audit
Scan a target's codebase before you sign. Get a defensible, standards-mapped findings report with an immutable audit trail.
OT / ICS repo review
Review operational-technology repositories aligned to ISA/IEC 62443 — ISA/IEC 62443 control mapping is planned (roadmap). Built for critical-infrastructure scrutiny.
Second opinion over existing SAST
Layer AIHarness over your current scanner to dedupe noise, explain findings in plain language, and surface evidence-graded confidence.
SBOM & supply-chain check
Generate a CycloneDX SBOM and check dependencies, aligning with SLSA and CISA guidance on software supply-chain integrity.
Trust & data governance
Built so an auditor can trust it
BYO key, shredded
Your Anthropic key is envelope-encrypted, used only for the job, then shredded. We never persist it.
Source kept only for the job
Code is retained only for the job's TTL, never used for training, then discarded.
Prompt-injection defense
Code is passed as data; the model fills a strict JSON schema and cannot be steered by content inside the scanned source.
Reproducible & audited
An immutable audit log records model id, version, prompt hash, and ruleset versions for every scan.
Model-agnostic by interface
A clean adapter abstracts Claude, OpenAI, and Gemini. Swap providers without changing the pipeline.
Honest accuracy posture
Evidence-based confidence. LLM-only findings are labeled “needs review,” never overclaimed as confirmed.
We scan ourselves
Our own self-scan, dated 2026-06-24
If we ask you to trust the harness, we run it on ourselves — and report it honestly.
0production-dependency vulnerabilities
148components in our CycloneDX SBOM
2.1.0SARIF output, schema-validated by automated test
- Manual review clean: BYO-key lifecycle, container path-traversal guard, parameterized SQL, XSS-safe DOM.
- Our SARIF output is validated by an automated test (ajv vs the official SARIF 2.1.0 schema).
- A CycloneDX SBOM (148 components) is committed to the repo (
sbom.json) and regenerated vianpm run sbom. - LLM-only findings are labeled “needs review” — we don't overclaim.