by imbue-ai · Agent Tool · ★ 132
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npm install -g latchkey
npx skills add imbue-ai/latchkeyTaken from the project's README on GitHub.
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.
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 | 132 |
| Forks | 5 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70/100 |
| Open Issues | 8 |
| Last Updated | 2026-11-05 |
| Created | 2026-01-15 |
| Platforms | node |
| Est. Tokens | ~18k |
Latchkey Inject API credentials into local agent requests. Full documentation Quick example Overview Latchkey is a command-line tool that injects credentials into curl commands. - List third-party services (Slack, Google Workspace, Linear, GitHub, etc.) that are supported out-of-the-box.
Looking for a latchkey alternative? If you're comparing latchkey 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.
The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
GoPeak — The most comprehensive MCP server for Godot Engine. 95+ tools: scene management, GDScript LSP, DAP de
Rails Engine with MCP compliant Spec.
Give your AI Agent a whole IDE, not just the files
A GitHub CLI extension that seamlessly runs the github-mcp-server using your existing gh authentication. Elimi
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: