EVA — security grade CAUTION, quality 66/100

Security audit verdict: CAUTION · quality 66/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ARCANGEL0 · Agent Tool · ★ 434

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is EVA safe to install? View the security audit →

About EVA

⫻ 𝝣.𝗩.𝝠 ⮡ Exploit Vector Agent Autonomous offensive security AI for guiding pentest processes [![Checkout my other project

ai-agentartificial-intelligenceautomationclictfcybersecurityethical-hackinglinuxllmllm-agent

Quick Facts

Stars434
Forks82
LanguagePython
CategoryAgent Tool
Quality Score65.8498594783157/100
Last Updated2026-06-16
Created2025-12-15
Platformscli, python
Est. Tokens~16k

Compatible Skills

These tools work well together with EVA for enhanced workflows:

  • mcp-security-hub — semantic(0.34)+complementary+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • deadend-cli — semantic(0.27)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)
  • fuzzforge_ai — semantic(0.29)+complementary+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • tengu — semantic(0.35)+complementary+rare_topics+same_lang+shared_platform (62%)
  • watchtower — semantic(0.22)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)

EVA alternative? Top 6 similar tools

Looking for a EVA alternative? If you're comparing EVA with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • pentest-ai-agents by 0xSteph · ⭐ 2.1k

    Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized pene

  • CyberStrike by CyberStrikeus · ⭐ 1.9k

    Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,

  • pentest-ai by 0xSteph · ⭐ 1.7k

    Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a

  • numasec by FrancescoStabile · ⭐ 466

    The AI Agent for Cyber Security.

  • skene by SkeneTechnologies · ⭐ 121

    Product-Led Growth (PLG) analysis toolkit that detects tech stacks, plans growth loops and builds the loop ite

  • AutoRedTeam-Orchestrator by Coff0xc · ⭐ 263

    MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is EVA?

EVA is EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.. It is categorized as a Agent Tool with 434 GitHub stars.

What programming language is EVA written in?

EVA is primarily written in Python. It covers topics such as ai-agent, artificial-intelligence, automation.

How do I install or use EVA?

You can find installation instructions and usage details in the EVA GitHub repository at github.com/ARCANGEL0/EVA. The project has 434 stars and 82 forks, indicating an active community.

What are the best alternatives to EVA?

The top alternatives to EVA on Agent Skills Hub include pentest-ai-agents, CyberStrike, pentest-ai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools