ai-security-tool
🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workflows, CTF & DevSecOps. Cross-platform & Web UI.
No outside reports on file
This tool needs high trust because it handles login credentials, connects to production systems, and sends security data to external AI services—use it only in isolated test environments and never with real production credentials.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionRuns shell or system commandsREVIEW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (ZeroDayEvil/ai-security-tool)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/ZeroDayEvil/ai-security-tool ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About AI Security Tool
This tool combines a security terminal with AI agents to scan systems for vulnerabilities, check for known security issues (CVEs), and run automated security tests. It can connect to remote machines via SSH, RDP, and other protocols, and uses AI models like DeepSeek or OpenAI to help analyze security problems.
Who it’s for
Security researchers, DevSecOps teams, and people doing capture-the-flag (CTF) competitions who want AI help finding and fixing vulnerabilities. It's designed for people comfortable with technical security tools.
Alternatives
- OpenVAS: Open-source vulnerability scanner with no AI, widely tested and established.
- Nessus: Commercial vulnerability scanner with strong CVE coverage and less external AI dependency.
- OWASP ZAP: Free web app security scanner, manual or script-driven, no autonomous AI agents.
- Trivy: Lightweight vulnerability scanner for containers and code, no remote access or AI features.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/ZeroDayEvil/ai-security-tool (opens external site) for installation and setup instructions. The project may provide package installation or Docker options—check their documentation for your system.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.3k
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Remote access credentials: The tool stores or handles SSH, RDP, and other login credentials to connect to your systems; if compromised, attackers gain access to those machines.
- AI model access: You send security data and code to external AI services (OpenAI, DeepSeek); sensitive details about your infrastructure could leak there.
- Privilege escalation: Running as root or with admin rights means any bug in the tool or injected code could take over your whole system.
- Malicious scan results: Specially crafted files or network responses could trick the AI agents into running harmful commands or misinterpreting safe data as threats.
- Web UI exposure: If the web interface is exposed to untrusted networks, attackers could access scan results, stored credentials, or run unauthorized scans.
How to lower the risk
Least-privilege permissions
- Run the tool with minimal permissions needed for its specific scans, never as root.
- Use dedicated, limited-access accounts for remote connections instead of admin credentials.
Network isolation
- Keep the tool and its web UI on isolated networks, not exposed to the internet.
- Restrict which machines it can reach; don't give it blanket access to your network.
Monitoring
- Log all scans, credentials used, and AI model interactions to spot unusual activity.
- Review what data the tool sends to external AI services before running it.
Red flags to watch for
- Unexpected network connections or high data uploads to AI service endpoints.
- Tool requesting admin/root permissions without clear reason for specific scans.
Questions
How do I install AI Security Tool?
AI Security Tool does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/ZeroDayEvil/ai-security-tool.
Are there security reports about AI Security Tool?
No reports found for this package in our research (last checked 2026-10-30). AI Security Tool currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include remote access credentials, ai model access, privilege escalation.
Is AI Security Tool actively maintained?
AI Security Tool has 1.3k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/ZeroDayEvil/ai-security-tool before pinning it in production.
What are alternatives to AI Security Tool?
Notable alternatives to AI Security Tool include OpenVAS (Open-source vulnerability review with no AI, widely tested and established), Nessus (Commercial vulnerability review with strong CVE coverage and less external AI dependency), OWASP ZAP (Free web app security review, manual or script-driven, no autonomous AI agents), Trivy (Lightweight vulnerability review for containers and code, no remote access or AI features). You can also compare AI Security Tool side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use AI Security Tool? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/zerodayevil-ai-security-tool)HTML embed:
<a href="https://agentarmorhq.com/skills/zerodayevil-ai-security-tool"><img src="https://agentarmorhq.com/api/badge/zerodayevil-ai-security-tool" alt="AgentArmorHQ Risk Grade for AI Security Tool" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "zerodayevil-ai-security-tool"Share with your security lead
Need sign-off to use ai-security-tool? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: ai-security-tool
- **Listing URL:** https://agentarmorhq.com/skills/zerodayevil-ai-security-tool
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.3k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** Runs shell or system commands
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (ZeroDayEvil/ai-security-tool)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/ZeroDayEvil/ai-security-tool
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- ZeroDayEvil
- Source code
- github.com/ZeroDayEvil/ai-security-tool
- Est. context load
- ~900 tokens / turn (~5 tool schemas, 0.45% of 200k context)
- Popularity
- 1.3k GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-23
Community
Discussions for AI Security Tool
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude