Pentest AI Agents

by 0xSteph• 2.4k•• Scanned•Claim this listing•Request removal
Security & Testingai agentsai securitybug bountyclaude codectf

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

Pentest AI Agents is an open-source ai agent by 0xSteph, written mainly in Shell, with 2,393 GitHub stars and the MIT license. Its code was last updated Oct 6, 2026.

Scan summary: scanned Nov 5, 2026 at commit e5d7aa0. No capabilities flagged by our checks. Scan policy

What Pentest AI Agents can touch

  • Run shell commandsNot seen in this scan
  • Run dynamic codeNot seen in this scan
  • Read or write filesNot seen in this scan
  • Read environment and secretsNot seen in this scan
  • Control a web browserNot seen in this scan
  • Connect to databasesNot seen in this scan
  • Read or send messagesNot seen in this scan
  • Touch money or tradingNot seen in this scan
  • Connect to the internetNot run in this scan

"Not seen" means our checks did not find it, and the tool may still do it. Covers commit e5d7aa0, Nov 5, 2026. See the scan policy.

Before you install Pentest AI Agents

AgenticMart scanned Pentest AI Agents on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What it can access

  • An AI agent decides its own next steps and calls whatever tools you give it, so its risk depends on the access you grant.

Before you install

  1. Pin the version you reviewed instead of always installing the latest release.
  2. Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
  • Maintained by 0xSteph on GitHub, 2,393 stars and 451 forks. Popularity is not proof of safety.
  • Last code change: Oct 6, 2026.
  • Open-source license: MIT.

Pentest AI Agents is an open-source ai agent by 0xSteph, written mainly in Shell. Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

At a glance

Stars
2.4k
Forks
451
Language
Shell
License
MIT
Created
Mar 2026
Last update
Oct 6, 2026
Type
AI Agent
Price
Free

Topics

ai-agentsai-securitybug-bountyclaude-codectfcybersecurityethical-hackinginfoseckali-linuxmitre-attackoffensive-securityoscppenetration-testingpentestpentestingred-teamsecurity-automationsecurity-tools

Questions about Pentest AI Agents

What is Pentest AI Agents?

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

Who maintains Pentest AI Agents?

Pentest AI Agents is maintained by 0xSteph on GitHub (0xSteph/pentest-ai-agents). AgenticMart lists it from public repository data.

Is Pentest AI Agents safe to use?

AgenticMart scanned Pentest AI Agents on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What license does Pentest AI Agents use?

It is published under the MIT license.

Pentest AI Agents alternatives

View more →

Similar ai agents in Security & Testing, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
Pentest AI Agents (this page)
0xSteph
2.4kMITOct 6, 2026Scanned, no flagged issues
ECC
affaan-m
294kMITOct 30, 2026Scanned, no flagged issues
Strix
usestrix
73kApache-2.0Oct 30, 2026Scanned, no flagged issues
Goose
aaif-goose
56kApache-2.0Nov 1, 2026Scanned, no flagged issues
Anthropic Cybersecurity Skills
mukul975
35kApache-2.0Aug 31, 2026Scanned, no flagged issues
Pentagi
vxcontrol
33kMITOct 22, 2026Scanned, no flagged issues