claude

sechelix

Evidence-first application-security Agent Skill. Maps attack surfaces, selects applicable security hypotheses, independently verifies material findings, refutes false positives, fixes root causes, requires regression proof, and produces explicit release decisions.

0 on GitHubby SecHelixv4.0.0-alpha.7Apache-2.0updated 1 month agosecurity
/

Plugin sechelix from marketplace sechelix in omarmohelal2/sechelix-marketplace. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (2)

  • sechelix

    Portable evidence-first application-security audit workflow for authorized systems. Use to review codebases, APIs, web apps, auth/authz, business logic, races, payments, supply chain, AI/MCP integrations, cloud/config, and releases. Also use for requested SEO audits and safe codebase cleanup via the

  • sechelix-lite

    Evidence-first application-security review for codebases, pull requests and environments the user is authorized to assess. Use when asked to security-review a repository or diff, audit authentication, authorization (IDOR/BOLA/BFLA), business logic, race conditions, injection, SSRF, file handling, su

Subagents (17)

  • ai-mcp-agent-security-reviewer

    Review agent identity, prompt/tool boundaries, MCP authorization, untrusted context, tool output and automatic side effects. Produce candidates only.

  • authentication-reviewer

    Review authentication, sessions, account recovery, MFA/step-up, cookies, tokens and federation. Produce candidates only.

  • authorization-bola-bfla-reviewer

    Review object and function authorization, roles, capabilities, BOLA/BFLA, tenant isolation and fail-open permission paths. Produce candidates only.

  • browser-extension-reviewer

    Review browser/client boundaries, DOM/origin behavior, extension privileges, messaging, storage and browser-only build/runtime exposure. Produce candidates only.

  • business-logic-reviewer

    Review workflow, entitlement, inventory, approval and state-machine abuse outside payment-specific accounting. Produce candidates only.

  • ci-cd-cloud-reviewer

    Review CI identities, workflow trust, secrets, artifacts, deployments, cloud policy and runtime configuration. Produce candidates only.

  • database-rls-migrations-reviewer

    Review database authorization, RLS, grants, functions, constraints, migrations and rollback safety. Produce candidates only.

  • independent-verifier

    Independently reconstruct and try to refute candidate security findings without assuming the claim or proposed severity is correct.

  • injection-web-reviewer

    Review SQL, command, template, HTML/DOM and expression injection plus XSS, CSRF, redirects and web security controls. Produce candidates only.

  • surface-mapper

    Map architecture, identities, assets, entrypoints, data flows and trust boundaries from repository evidence. Produce a map and candidate hypotheses, never final vulnerabilities.

  • payments-accounting-reviewer

    Review money, prices, currencies, refunds, payouts, settlement, ledger and reconciliation invariants. Produce candidates only.

  • privacy-logging-reviewer

    Review collection, minimization, logging, telemetry, redaction, retention and privacy-sensitive data flows. Produce candidates only.

  • race-idempotency-reviewer

    Review concurrency, retries, duplicate callbacks, TOCTOU, process crash and exact-once/idempotency controls. Produce candidates only.

  • regression-release-verifier

    Verify behavioral regression proof, neighboring controls and release-readiness evidence after remediation without substituting scanner output for proof.

  • remediation-reviewer

    Review verified root causes and design canonical, compatibility-aware remediations with explicit preservation and regression requirements.

  • ssrf-file-parser-reviewer

    Review outbound requests, URL validation, uploads, filesystem paths, archives and document/media/parser boundaries. Produce candidates only.

  • supply-chain-reviewer

    Review dependencies, packages, lockfiles, install/build inputs, provenance and artifact integrity. Produce candidates only.

View source on GitHub sechelix.com

Similar plugins

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

anthropics/claude-code 155,476

Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening

5 skills · 3 commands · 2 agents

wshobson/agents 42,461

818 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more. Mapped to 6 frameworks.

200 skills

mukul975/Anthropic-Cybersecurity-Skills 36,021

Moved to phuryn/product-engineering, which maintains the AI Shipping Kit in its ai-shipping plugin; the skills and commands here only say where each one went.

3 skills · 5 commands

phuryn/pm-skills 27,939

Maintain sechelix?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted