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 yhzhu99 · Agent Tool · ★ 54
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is HealthFlow safe to install? View the security audit →
HealthFlow HealthFlow is a strategically self-evolving multi-agent framework for automating electronic health record (EHR) analysis. It turns a clinical analysis request into a governed workflow that plans, executes, evaluates, repairs, and writes back reusable experience for later tasks. The system is organized around four agents: Meta agent: profiles the task, retrieves bounded EHR-aware experience, and produces an attempt-specific plan. Executor agent: turns the plan into code, tool calls, and analytical artifacts through an external coding-agent backend. Evaluator agent: reviews execution traces and artifacts for runtime failures and EHR validity risks. Reflector agent: synthesizes reusable safeguards, workflows, dataset anchors, and code snippets from completed trajectories. Useful links: Project website: Static app demo: Live runtime: Human evaluation platform: Code repository: <https://github.
| Stars | 54 |
| Forks | 4 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 65.0118373901309/100 |
| Last Updated | 2026-09-22 |
| Created | 2025-05-28 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with HealthFlow for enhanced workflows:
Looking for a HealthFlow alternative? If you're comparing HealthFlow 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.
[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Re
Python SDK for healthcare AI — typed, validated FHIR tools for agents, real-time EHR connectivity, production
Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focu
TypeScript template for building Model Context Protocol (MCP) servers. Ships with declarative tools/resources,
Explore other popular agent tool tools:
HealthFlow is [npj Digital Medicine 2026] HealthFlow: Automating electronic health record analysis via a strategically self-evolving multi-agent framework. It is categorized as a Agent Tool with 54 GitHub stars.
HealthFlow is primarily written in Python. It covers topics such as ai-for-healthcare, ai-for-science, ehr.
You can find installation instructions and usage details in the HealthFlow GitHub repository at github.com/yhzhu99/HealthFlow. The project has 54 stars and 4 forks, indicating an active community.
The top alternatives to HealthFlow on Agent Skills Hub include EhrAgent, HealthChain, captain-claw. 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: