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 PangHu1020 · Agent Tool · ★ 77
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is scholar-rag safe to install? View the security audit →
ScholarRAG Multi-Agent RAG System for Academic Paper Q&A Upload academic papers, ask questions in natural language, get grounded answers with precise citations. Quick Start API Reference [!NOTE] Still undergoing continuous optimization and updates... What is ScholarRAG? https://github.com/user-attachments/assets/5f9d36e9-9027-4fcd-b0f4-b0dee7d123a3 ScholarRAG is an end-to-end academic paper Q&A system. It parses PDFs with full structural awareness (sections, tables, figures), retrieves relevant passages via hybrid search, and generates cited answers through a multi-agent pipeline -- all accessible through a clean chat interface. Key highlights: Multi-agent query decomposition with parallel retrieval and self-reflection Hybrid BM25 + dense retrieval with cross-encoder reranking Structured PDF parsing preserving section hierarchy, tables, figures, formulas, and captions Smart OCR fallback: fast text extraction by default, OCR only when needed
| Stars | 77 |
| Forks | 9 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 63.3895334233944/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-19 |
| Created | 2026-03-29 |
| Platforms | python |
| Est. Tokens | ~3079k |
Explore other popular agent tool tools:
scholar-rag is A beginner-friendly and extensible Agentic RAG project that demonstrates the full pipeline of document parsing, retrieval, reranking, workflow orchestration, tool calling, and answer generation, desig. It is categorized as a Agent Tool with 77 GitHub stars.
scholar-rag is primarily written in Python.
You can find installation instructions and usage details in the scholar-rag GitHub repository at github.com/PangHu1020/scholar-rag. The project has 77 stars and 9 forks, indicating an active community.
scholar-rag is released under the MIT license, making it free to use and modify according to the license terms.
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: