Epherem

Epherem is a security scanner that finds vulnerabilities in applications built with artificial intelligence.

Epherem is a security scanner designed for applications built with artificial intelligence tools like Lovable, Bolt, v0, Replit, Cursor, and Claude Code. Users can upload a ZIP file or connect a GitHub repository to scan code, settings files, and packages for vulnerabilities. The scanner performs fifty-five checks to find exposed keys, open database tables, missing login and ownership checks, and unsafe input. Every finding displays the specific file, line, and code, along with a prompt to paste into an AI tool for repair. The platform categorizes findings into known issues, likely issues, checks that need review, and items it could not read.

Epherem at a glance

Best for: Software engineer
Runs on: Web
Pricing: Free during early access, 5 scans a day
Released: October 2026
Category: AI coding tool
Website: epherem.com

Key features

Upload a ZIP project or connect GitHub
Scan code, settings files, and package lists
Perform 55 checks for common security mistakes
Check dependencies against published advisories
View specific file, line, and code for each finding
Get AI fix prompts for Cursor, Lovable, or Claude Code
Receive a report detailing unread or unchecked items

Use it for

Scan AI-built applications for security vulnerabilities
Check dependencies against published security advisories
Identify exposed keys and open database tables
Generate repair prompts for AI coding tools

Alternatives to Epherem

Cohere — Private, secure enterprise AI deployment with customizable models.
ShipOrNah — Checks AI-generated apps for exposed API keys and missing Supabase RLS.
SkillTotal — Scans code locally without accounts, telemetry, API tokens or executing the files.
Oss Scanner — It builds projects in isolated VMs and emails model-generated reports with patches.
Pixee — Automates vulnerability triage and generates actionable code fixes.
New Relic — Unified visibility across applications, infrastructure, and AI models.
ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture.
OpenAPPA — Tracks data flows algebraically to prevent prompt injection without breaking agents.
Cisco Skill Scanner — Combines pattern matching, dataflow analysis, and an optional LLM judge for threat detection.
Robusta — Reduces costs and noise by investigating unique incidents instead of raw alerts.
Semgrep — Unifies SAST, SCA, and secrets scanning with AI-assisted noise filtering.
HackerOne — Combines AI agents with expert human researchers to prioritize and fix real risks.

All Epherem alternatives