User repository on GitHub
Python script that uses Jev.ai to score whether a vulnerability has real security impact
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
JevImpact
A Python script that scores an AI agent's documented security finding with TypeSafe's Jev model, returning JSON with is_vulnerability, impactful and an impact_score from 0 to 1. It accepts structured JSON or a full text or Markdown report and can be imported by another agent.
- Stars
- 4
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- mhaskar
- Last verified
- Oct 2026
Highlights
- Returns is_vulnerability, impactful and impact_score from 0 to 1 as JSON, per the README.
- Accepts structured JSON findings or a complete text or Markdown report; stdin works with - and --format json.
- JSON input requires title, description, exploitation_steps and impact; unknown fields are rejected to catch mistakes.
- All included example findings are synthetic; the README says to supply real context for your own reports.
- Created and pushed 2026-10-02, 4 stars, no license listed; it uses the same SDK as the existing TypeSafe examples.
Quickstart
bash
python3 -m pip install -r requirements.txt
export TYPESAFE_API_KEY='your-key'
python3 JevImpact.py examples/invoice_idor.json
cat examples/invoice_idor.json | python3 JevImpact.py - --format jsonWatch out
README reviewed 2026-10-17; all example findings are synthetic, no accuracy or calibration figures are given, and the GitHub description loosely says Jev.ai while the README links TypeSafe's SDK.
Questions about this entry
Short answers drawn from the linked project or page.
It is a Python script that uses TypeSafe's Jev model to score whether a documented vulnerability finding has real security impact. It returns JSON with is_vulnerability, impactful and an impact_score from 0 to 1.
It assesses an AI agent's finding with TypeSafe's Jev model through the same SDK as the existing examples, and the README notes the script is also importable so another agent can call it programmatically.
Structured JSON or a complete text or Markdown report. JSON requires title, description, exploitation_steps (a nonempty list of strings) and impact; evidence and context are optional, and unknown JSON fields are rejected.
Install requirements, set TYPESAFE_API_KEY, then run python3 JevImpact.py with a JSON file or Markdown report; piping works too, for example cat finding.json | python3 JevImpact.py - --format json.
No, all included findings are synthetic, per the README, including examples/invoice_idor.json and examples/blind_ssrf.json. For your own reports you should supply the bug description, exploitation steps, impact, evidence and deployment context.
The digest shows no accuracy, calibration or benchmark figures; it describes what the tool returns and how to feed it, and the impact_score is Jev's output rather than a validated metric.
The GitHub user mhaskar. The repository was created and last pushed 2026-10-02, with 4 stars and no forks when the sweep ran; no license is listed in the metadata.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Show HN: Ad Spend Guard gates budget before the auction, not the creative after.
Show HN: Gating ad budget with a decision modelRead the thread on Hacker NewsX: Field Advisory sends marginal readings to an agronomist instead of a spray.
This post couldn't be loaded here — read it on X.https://x.com/agriwisehq/status/2781000000000000003YouTube: 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 NewsMore Jev resources like this
A proof-of-concept Python scanner that maps a backend codebase's attack surface and ranks likely vulnerabilities down to the suspicious line, using Jev as the classifier for about one cent per repo. It reads Python, JavaScript and TypeScript, and a demo site shows read-only results on PyGoat and NodeGoat.
Jev Tools & CLIs#community#github#security
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
cisco-ai-defense/skill-scannerPythonPython CLI and agent skill that reviews Agent Skills, MCP configs, and source code for suspicious behavior with TypeSafe Jev plus local static checks, reporting file and line evidence, risk categories, model probabilities, and unscanned scope.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
win4r/jev-security-scanPython
win4r/jev-security-scanPythonSupervisor 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
VeridicalTech/EdwardPythonA safety guardrail for coding agents (Claude Code, Codex, Cursor, Antigravity, Grok) that intercepts shell commands, script executions and file writes before they run. Its neural tier can use Liquid AI d1-3B, CLM, TypeSafe Jev cloud or pure rules; a deterministic tier blocks destructive patterns in under 0.1 ms.
Jev Tools & CLIs#community#github#security
Community
Bl4ckk01/agent-guardrailPython
Bl4ckk01/agent-guardrailPythonA 2.4 GHz WiFi site-survey instrument built on a ZimaBoard 2 and an Alfa USB adapter: Python and Scapy turn captured 802.11 frames into structured RF telemetry, and Jev reads each measurement window through OpenRouter to return coverage, congestion and optimization decisions.
Jev Tools & CLIs#community#github#wifi
Community
ronibandini/jevwifianalyzer-Python
ronibandini/jevwifianalyzer-PythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.