---
title: "sechelix"
description: "Evidence-first application-security Agent Skill for repositories and environments you are authorized to test. Maps the attack surface, selects applicable security hypotheses from a 546-item catalog, hunts in parallel acr"
canonical: https://agentpluginsdirectory.com/plugins/sechelix
last-updated: 2026-09-21
---

# sechelix
Evidence-first application-security Agent Skill for repositories and environments you are authorized to test. Maps the attack surface, selects applicable security hypotheses from a 546-item catalog, hunts in parallel across specialist roles, then sends every candidate to an independent verifier whose job is to disprove it. Applicability resolves to APPLICABLE, NOT_APPLICABLE, UNKNOWN or BLOCKED so missing evidence is never read as absence; High and Critical findings require regression proof; and the release gate is fail-closed, returning PASS, PASS_WITH_KNOWN_RISK, BLOCKED or INCOMPLETE. Includes an UNTRUSTED_REPO mode that treats repository content as data and never as control instructions.
- Slug: sechelix
- Publisher: Omar
- Repository: https://github.com/omarmohelal/SecHelix
- Manifest: plugin.json
- Version: 4.0.0-alpha.7
- License: Apache-2.0
- Category (editorial): other
- Skills: 1 (sechelix)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-08-31
- Repository last pushed: 2026-09-21
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/sechelix
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What sechelix does, in the publisher's words

Most AI security tools try to find more. SecHelix tries to prove itself wrong.

Every candidate finding goes to an independent verifier whose only job is to disprove it. The report shows you what it refuted and why, and returns INCOMPLETE rather than a clean PASS when it could not actually check.

Open source, Apache-2.0, for code you own or are authorized to test. Runs in Claude Code, Codex, Copilot and other Agent Skills-compatible agents; the Python runtime is optional.

- map the attack surface and trust boundaries;
- review only security checks that apply to the project;
- investigate authentication, authorization, business logic, injection, SSRF, files, supply chain, AI/MCP and other security surfaces;
- verify important candidates instead of reporting guesses;

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/omarmohelal/SecHelix/HEAD/README.md

## Skills

- sechelix: Evidence-first application-security audit workflow for authorized repositories and environments. Use when reviewing a codebase, pull request, API, web application, AI-generated code, agent or MCP integration, cloud configuration, authorization (BOLA, IDOR, BFLA), business logic, payments, race cond…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.