by cohere-ai · Agent Tool · ★ 173
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.
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 | 173 |
| Forks | 31 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70/100 |
| Open Issues | 12 |
| Last Updated | 2023-08-14 |
| Created | 2022-10-24 |
| Platforms | python |
| Est. Tokens | ~124k |
################################################################################ # / # ' \ / \ \/ / # () < # \\/./ \//\\ # # This project is part of Cohere Sandbox, Cohere's Experimental Open Source # offering. This project provides a library, tooling, or demo making use of # the Cohere Platform. You should expect (self-)documented, high quality code # but be warned that this is EXPERIMENTAL.
Looking for a sandbox-conversant-lib alternative? If you're comparing sandbox-conversant-lib 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.
GoalChain for goal-orientated LLM conversation flows
LLMs and Machine Learning done easily
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 19+ LLM provi
A lightweight, open, and extensible multi-LLM interaction studio.
Roy: A lightweight, model-agnostic framework for crafting advanced multi-agent systems using large language mo
Modern AI chatbot supporting multiple LLMs. Switch between Gemini, Mistral, Llama, Claude and ChatGPT.
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: