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 pillumina · Agent Tool · ★ 5
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ascend-sleuth safe to install? View the security audit →
知识驱动的昇腾训练/推理诊断 skill 套件 — Ascend training/inference diagnosis skill suite (5 skills + 3-tier knowledge base, Agent Skills standard)
| Stars | 5 |
| Forks | 0 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 57.9950560729348/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-03 |
| Created | 2026-07-28 |
| Platforms | claude-code, python |
| Est. Tokens | ~17k |
Looking for a ascend-sleuth alternative? If you're comparing ascend-sleuth with other agent tool tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads,
Give your AI Agent a whole IDE, not just the files
Explore other popular agent tool tools:
ascend-sleuth is 知识驱动的昇腾训练/推理诊断 skill 套件 — Ascend training/inference diagnosis skill suite (5 skills + 3-tier knowledge base, Agent Skills standard). It is categorized as a Agent Tool with 5 GitHub stars.
ascend-sleuth is primarily written in Python. It covers topics such as agent-skills, ascend, claude-code.
You can find installation instructions and usage details in the ascend-sleuth GitHub repository at github.com/pillumina/ascend-sleuth. The project has 5 stars and 0 forks, indicating an active community.
ascend-sleuth is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ascend-sleuth on Agent Skills Hub include kaggle-skill, mcp-steroid. 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: