No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by 0xSteph · Agent Tool · ★ 2.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pentest-ai-agents safe to install? View the security audit →
pentest-ai Turn Claude Code into your offensive security research assistant. 28 specialized AI subagents for every phase of authorized penetration testing, from scoping to reporting. 6 Tier 2 agents that execute tools directly with your approval. Autonomous exploit chaining. PoC-validated findings. Agentic swarm orchestration. Business logic flaw detection. CI/CD pipeline integration. MITRE ATT&CK mapped. Dual offensive/defensive perspective in every response. []() []() []() []() [](https://
| Stars | 2,131 |
| Forks | 406 |
| Language | Shell |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70.0281462437288/100 |
| Open Issues | 2 |
| Last Updated | 2026-08-16 |
| Created | 2026-03-28 |
| Platforms | claude-code, cli |
| Est. Tokens | ~22k |
These tools work well together with pentest-ai-agents for enhanced workflows:
Looking for a pentest-ai-agents alternative? If you're comparing pentest-ai-agents 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.
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disc
An agent-native red-teaming workspace with a fast browser, direct HTTP traffic control, sandboxed execution, a
The AI Agent for Cyber Security.
Reconmap is a collaboration-first security operations platform for infosec teams and MSSPs, enabling end‑to‑en
AI-powered subdomain enumeration tool with local LLM analysis via Ollama - 100% private, zero API costs
Explore other popular agent tool tools:
pentest-ai-agents is Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audi. It is categorized as a Agent Tool with 2.1k GitHub stars.
pentest-ai-agents is primarily written in Shell. It covers topics such as ai-agents, ai-security, bug-bounty.
You can find installation instructions and usage details in the pentest-ai-agents GitHub repository at github.com/0xSteph/pentest-ai-agents. The project has 2.1k stars and 406 forks, indicating an active community.
pentest-ai-agents is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to pentest-ai-agents on Agent Skills Hub include CyberStrike, Claude-BugHunter, h5i. 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: