Does NucleiSniper skip templates?

No. It prioritises rather than filters: every template still runs, ordered by its Jev relevance score. The optional prefilter only drops templates that cannot match, such as code/file templates and unmatched product tags, and flags like --scan-min-score or --severity apply a hard cut.

What information does Jev see for each template?

Each batch of about 50 templates includes the target's 30+ signal profile plus template id, name, description, severity, tags, protocols, path hints and matcher words, answered on a 0-4 relevance rubric that returns probabilities, an expected-value score and a confidence.

What do I need installed before NucleiSniper can run?

Python 3.10 or higher, Nuclei on PATH with its templates cloned, and a TYPESAFE_API_KEY. If nuclei is not on PATH the script stops before calling Jev, so no API credit is spent.

How much does the prefilter cut Jev scoring cost?

It drops templates that cannot match, keeping about 8.6% of 13,764 templates at 100% recall on score >= 3. The README reports that turns roughly 6.19M tokens of scoring into about 495K, close to a 91% saving.

Why does NucleiSniper build a SQLite template index?

The first stage parses nuclei-templates YAML metadata into a SQLite index and re-parses only changed files. The README says this saves about 70 seconds on a catalog of 13,000-plus templates on later runs.

Can I score first and scan later without paying twice?

--no-scan writes a relevance.json report after scoring, and --report relevance.json runs Nuclei from that saved report without re-scoring. --resume reuses stored scores from SQLite after an interrupted run.

How consistent are the Jev relevance scores between runs?

Measured on itsecgames.com, the README reports MAE 0.043 for the same payload re-run but 0.273 for the same template in a different batch, so a template's score depends somewhat on the batch it was scored in.

CommunityJev Tools & CLIs

NucleiSniper

Scanner pipeline that fingerprints each target with 30+ signal types, then asks Jev to score every Nuclei template 0-4 for relevance so high-value checks run first while all templates still run. A tag-based prefilter keeps about 8.6% of 13,764 templates with 100% recall on score >= 3, saving ~91% of scoring tokens.

See highlights

Open github.com

Stars: 16
Language: Python
Published by: Community
Last verified: Oct 2026

MorDavid/NucleiSniper

User repository on GitHub

View on GitHub

AI-powered Nuclei template prioritization using deep target fingerprinting and TypeSafe Jev to surface relevant security findings faster.

Forks: 6
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

Run every Nuclei template — highest-relevance first — powered by TypeSafe Jev AI scoring. Features • Installation • Usage • Examples • How Scoring Works • Configuration • Disclaimer. NucleiSniper is a single-script pipeline that uses TypeSafe Jev AI to rank all Nuclei templates by relevance to each target, then runs Nuclei with the most-relevant templates first. Stage 1 (Profile & Score): Deep-fingerprint each target, then send template batches to Jev AI for relevance scoring (0–4)

Quoted from the project's README. Read the full README.

Tagscommunity security nuclei vulnerability-scanning

Works forJev for Scoring Jev for Ranking

Used inJev for Security & Privacy

Languages: Python
Platforms: CLI Playwright
Capabilities: Requires API keySelf-hosted

Highlights

Jev returns a 5-point probability distribution per template, an expected-value score and confidence.
Prefilter keeps ~8.6% of 13,764 templates at 100% recall on score>=3, saving 6.19M to ~495K tokens.
Benchmark on itsecgames.com: same-payload non-determinism MAE 0.043, batch-dependence MAE 0.273.
The second stage runs Nuclei with templates ordered by score; --resume reuses SQLite scores.

Watch out

No license is declared in the repository metadata; GitHub reports NOASSERTION, so terms of reuse are unclear. Ordering is best-effort because Nuclei runs templates concurrently, and scanning third-party targets requires authorisation.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

YouTube: Kubernetes admission control with a decision model, fail-closed.

Hacker News: SafeDep Gryph plus Jev checks for compromised coding-agent behavior.

2 pointsDetecting Compromised AI Coding Agents with Jev and GryphRead the thread on Hacker News

Hacker News: Show HN: Agent Chaperone screens tool calls and results with Jev before the agent sees them.

sepehrsafari5 pointsShow HN: Agent Chaperone – Screen AI agent tool calls and results with JevRead the thread on Hacker News

X: Secret detection with Jev, tested

More Jev resources like this

Skill Scanner

2.6k

Cisco's security scanner for agent skills added a System One analyzer: it sends the full skill text to POST /v1/systemone as one advisory Noul question and records the probability, while being deliberately unable to emit a finding or change a severity.

Jev Tools & CLIs#community#security#agent-skills

Community

cisco-ai-defense/skill-scannerPython

jev-secret-guard

A Claude Code PreToolUse hook that blocks known key formats locally and sends only masked unknown high-entropy strings to Jev for a Noul judgment, blocking at 0.80 and asking the human from 0.30 or whenever Jev is unavailable.

Jev Tools & CLIs#community#security#claude-code

Community

BasmaAbouzied0/jev-secret-guardPython

pyGPT

A desktop AI assistant with a Jev / System One inline plugin for classification, routing, verification, and scoring without chat-style output.

Jev Tools & CLIs#community#python#desktop

Community

szczyglis-dev/py-gptPython

jev-guard (exchange triage)

A Java gateway that asks Jev four questions about a deposit or withdrawal, then applies a direction-aware routing matrix in code.

Jev Tools & CLIs#community#java#security

Community

klauswg/jev-guardJava

Ring Zero Security

Kernel-enforced runtime security for AI agents with eBPF/LSM: policy decides file, exec, package-install and MCP operations at the syscall, while Jev can run as an optional checks provider whose verdict can only raise severity. The Jev checks layer is off by default.

Jev Tools & CLIs#community#security#ebpf

Community

ringzerosec/jev-runtime-securityRust

Edward

Supervisor for unattended coding agents: it tracks cross-turn state and asks one batched Jev Choice whether a trajectory should continue, pause or escalate, while deterministic code owns dangerous-command blocking, budget caps and Ed25519-signed receipts.

Jev Tools & CLIs#community#guardrails#safety

Community

VeridicalTech/EdwardPython

From the Jev guides

Original write-ups on what this entry is for.

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

Exporting Decision Models: GGUF, ONNX, and Device Runtimes

Oct 10, 2026

Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.

Jev Tools & CLIs#open-models#local#onnx

Read article

Records at Rest: Documents, Inboxes, and Risk Queues

Sep 28, 2026

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.

Jev Tools & CLIs#classification#email#security

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai