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 jentic · Codex Skill · ★ 130
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jentic-mini safe to install? View the security audit →
Give your AI agents access to 10,000+ APIs — without leaking a single credential. Building agents that call real APIs is painful. You end up hardcoding auth, juggling secrets in prompts, writing bespoke glue code for every service, and praying nothing leaks. Jentic Mini fixes this. It's a self-hosted API execution layer that sits between your agent and the outside world. Your agent says what it wants to do. Jentic Mini handles the how — finding the right API, injecting credentials at runtime, and brokering the request. Secrets never touch the agent. Ever. ⚠️ Early Access — Jentic Mini is new and under active development. It may contain bugs, rough edges, and security gaps we haven't found yet. It is not recommended for production use at this stage. We're sharing it early so the communi
| Stars | 130 |
| Forks | 14 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 75.9083429961035/100 |
| Open Issues | 63 |
| Last Updated | 2026-06-30 |
| Created | 2026-03-19 |
| Platforms | node |
| Est. Tokens | ~18k |
Looking for a jentic-mini alternative? If you're comparing jentic-mini with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headles
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TO
A lightweight dependency-free workflow automation platform. Supports iPaaS, stream computing, MCP, and AI capa
The best way to build a personality for your agent. Let Claude Code / OpenClaw ingest your data & build your A
Explore other popular codex skill tools:
jentic-mini is Self-hosted API execution layer that sits between your agent and the outside world. Your agent says what it wants to do. Jentic Mini handles the how — finding the right API, injecting credentials at r. It is categorized as a Codex Skill with 130 GitHub stars.
jentic-mini is primarily written in TypeScript. It covers topics such as agents, ai, ai-agents.
You can find installation instructions and usage details in the jentic-mini GitHub repository at github.com/jentic/jentic-mini. The project has 130 stars and 14 forks, indicating an active community.
jentic-mini is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to jentic-mini on Agent Skills Hub include authsome, n8n-claw, kindly-web-search-mcp-server. 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: