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 →
⫻ 𝝣.𝗩.𝝠 ⮡ Exploit Vector Agent Autonomous offensive security AI for guiding pentest processes [![Checkout my other project
| Stars | 434 |
| Forks | 82 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 65.8498594783157/100 |
| Last Updated | 2026-06-16 |
| Created | 2025-12-15 |
| Platforms | cli, python |
| Est. Tokens | ~16k |
These tools work well together with EVA for enhanced workflows:
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.
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized pene
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a
The AI Agent for Cyber Security.
Product-Led Growth (PLG) analysis toolkit that detects tech stacks, plans growth loops and builds the loop ite
MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface
Explore other popular agent tool tools:
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.
EVA is primarily written in Python. It covers topics such as ai-agent, artificial-intelligence, automation.
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.
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.
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: