Skip to main content

VibeSec 🛡️

Autonomous AI & Application Security Platform: SAST, Secrets, Polyglot SCA, and Verified Auto-Remediation — engineered by CyberEiche under the CyberEiche security ecosystem alongside cybereiche-mcp-sec.

Tests Python Target Truth CyberEiche License

VibeSec is a privacy-first, developer-friendly security scanner designed to catch vulnerabilities, hardcoded secrets, dependency CVEs, and AI/LLM safety risks (OWASP Top 10 for LLMs) before code reaches production.


Key Features

  • Target Truth Validation: Reachability-driven active verification layer (DNS → TCP → HTTP) ensuring zero-noise and confirmed endpoint reachability.
  • AI & LLM Security Rules: Specialized AST patterns detecting prompt injection, agent shell execution, insecure deserialization, and unvalidated LLM outputs.
  • Unified Scanning Triad:
    • SAST: Multi-language static analysis powered by Semgrep and custom security rulesets.
    • Secrets: High-entropy credential and API token detection (Gitleaks & Yelp detect-secrets).
    • Polyglot SCA: Zero-runtime lockfile scanning powered by Google OSV (osv.dev) across Python, JavaScript/TypeScript, Go, Rust, Java, PHP, Ruby, and .NET.
  • 100% Code Privacy & Data Sovereignty: Scans run entirely on your local machine or your GitHub Actions runner. Your source code never leaves your infrastructure.
  • Zero-Setup GitHub Actions: Native PR annotations (::error::), formatted $GITHUB_STEP_SUMMARY audit reports, and OASIS SARIF v2.1.0 output for the GitHub Security tab without needing third-party bot tokens.
  • Autonomous Verified Remediation: Synthesizes localized patch diffs and verifies them against syntax checks and automated test suites before suggesting changes.

Quickstart

Installation

pip install cybereiche-vibesec

CLI Usage

# Run a full security scan on current directory
vibesec scan .

# Scan with high-severity threshold and SARIF output
vibesec scan . --severity HIGH --sarif vibesec-results.sarif

# Preview automatic fixes for detected issues (dry-run)
vibesec fix . --dry-run

# Apply verified fixes in-place
vibesec fix . --apply

Autonomous Remediation & LLM Configuration

VibeSec synthesizes localized security patches and verifies them against AST syntax checks and your local test suite before applying changes. Powered by LiteLLM, it supports Anthropic, OpenAI, DeepSeek, and self-hosted models.

1. Configure via .env

Add your preferred provider credentials to .env:

# 1. Anthropic (Claude - Default)
ANTHROPIC_API_KEY="sk-ant-..."

# 2. OpenAI (GPT-4o)
OPENAI_API_KEY="sk-proj-..."

# 3. DeepSeek
DEEPSEEK_API_KEY="sk-..."

# Optional: Custom/Local Gateway (Ollama, vLLM, internal proxy)
# VIBESEC_LLM_MODEL="ollama/llama3"
# VIBESEC_LLM_API_BASE="http://localhost:11434/v1"

2. Configure via .vibesec.yaml (Optional)

remediation:
  enabled: true
  model: "claude-3-5-sonnet-20241022" # or gpt-4o, deepseek/deepseek-chat

3. CLI Overrides

# Apply fixes only if local unit tests (pytest / npm test) pass
vibesec fix . --apply --run-tests

# Override model at runtime
vibesec fix . --model gpt-4o --apply

GitHub Actions Integration

Add VibeSec to your repository with 4 lines in .github/workflows/security.yml:

name: VibeSec Security & AI Guardrails

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

jobs:
  security-audit:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout Repository
        uses: actions/checkout@v4

      - name: Run VibeSec Security Audit
        uses: cybereiche/vibesec@v1
        with:
          severity: HIGH
          sarif_output: vibesec-results.sarif

      - name: Upload SARIF to GitHub Security Tab
        if: always()
        uses: github/codeql-action/upload-sarif@v3
        with:
          sarif_file: vibesec-results.sarif

Configuration (.vibesec.yaml)

Customize VibeSec behavior by adding a .vibesec.yaml file to your project root:

version: 1

settings:
  severity_threshold: "HIGH" # LOW | MEDIUM | HIGH | CRITICAL
  fail_on_findings: true

scanners:
  sast:
    enabled: true
  secrets:
    enabled: true
  sca:
    enabled: true

ignore:
  paths:
    - "tests/**"
    - "docs/**"
    - "node_modules/**"

Target Truth Validation

VibeSec incorporates CyberEiche's Target Truth active verification methodology. Live probes and findings undergo reachability validation across DNS resolution, TCP socket connection, and HTTP response states, ensuring actionable security findings with zero false positives.


License

VibeSec is distributed under the Apache 2.0 License.
Developed and maintained by CyberEiche.


About CyberEiche

CyberEiche is an enterprise cybersecurity firm specializing in autonomous AI defense, application security, and protocol verification.

Metadata

Release files for cybereiche-vibesec 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cybereiche-vibesec 0.1.1
File Size Uploaded Provenance Actions
cybereiche_vibesec-0.1.1.tar.gz 62.6 kB Without provenance Details for cybereiche_vibesec-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for cybereiche-vibesec 0.1.1
File Interpreter ABI Platform Actions
cybereiche_vibesec-0.1.1-py3-none-any.whl Python 3 none any Details for cybereiche_vibesec-0.1.1-py3-none-any.whl

Total release size: 124.8 kB

Release files / cybereiche_vibesec-0.1.1.tar.gz

Download URL cybereiche_vibesec-0.1.1.tar.gz
Size 62.6 kB
Tags Source
SHA-256 checksum
How to use checksums
57d29126038a10037aad0b0df030ba3710aba477bacc5c066cd665bc591d5b3c
BLAKE2b-256 checksum
How to use checksums
44e8f700caa2dc36fb9568507f8e5454b544e65d29bc05abf738377056773b03
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.15

Release files / cybereiche_vibesec-0.1.1-py3-none-any.whl

Download URL cybereiche_vibesec-0.1.1-py3-none-any.whl
Size 62.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7258820943dc8038928984c42bc85526751d6794484651c426b34c7ea4c4a665
BLAKE2b-256 checksum
How to use checksums
3bc07fe11c6753b0470d278c6d936f53be729836ffe99738caf9cf4038793438
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.15

Security for cybereiche-vibesec 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page