by s0ld13rr · Agent Tool · ★ 884
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 884 |
| Forks | 139 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 74/100 |
| Open Issues | 5 |
| Last Updated | 2026-10-23 |
| Created | 2026-07-08 |
| Platforms | node |
| Est. Tokens | ~16k |
PentestCode AI penetration testing agent in your terminal. Multi-agent architecture • Engagement state tracking • 20+ LLM providers PentestCode is an AI pentesting agent that runs tools, analyzes results, and makes decisions in your terminal. Hard fork of OpenCode (MIT), rebuilt for offensive security. Alpha — works on real engagements and CTFs, but expect rough edges.
Looking for a pentestcode alternative? If you're comparing pentestcode 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
Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, a
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,
Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory,
The AI Agent for Cyber Security.
Command a fleet of AI agents, on every deck, every desk, every wrist. Self-hosted multi-agent platform with me
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: