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 facebookresearch · Agent Tool · ★ 1.3k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is llm-transparency-tool safe to install? View the security audit →
Key functionality Choose your model, choose or add your prompt, run the inference. Browse contribution graph. Select the token to build the graph from. Tune the contribution threshold. Select representation of any token after any block. For the representation, see its projection to the output vocabulary, see which tokens were promoted/suppressed but the previous block. The following things are clickable: Edges. That shows more info about the contributing attention head. Heads when an edge is selected. You can see what this head is promoting/suppressing. FFN blocks (little squares on the graph). Neurons when an FFN block is selected. Installation Dockerized running Local Installation bash download git clone git@github.com:facebookresearch/llm-transparency-tool.git cd llm-transparency-tool install the necessary packages conda env create --name llmtt -f env.yaml install the package pip install -e . now, we need to build the
| Stars | 1,254 |
| Forks | 104 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 68.518457119272/100 |
| Open Issues | 9 |
| Last Updated | 2024-12-03 |
| Created | 2023-12-21 |
| Platforms | python |
| Est. Tokens | ~2k |
Looking for a llm-transparency-tool alternative? If you're comparing llm-transparency-tool 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.
Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw di
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜🤝 Infistar.cc 赞助 · 注册送
General-purpose Playwright automation for coding agents
This repository contains a collection of Agent Skills developed by GudaStudio, enabling seamless collaboration
A collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Andr
Explore other popular agent tool tools:
llm-transparency-tool is LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-. It is categorized as a Agent Tool with 1.3k GitHub stars.
llm-transparency-tool is primarily written in Python.
You can find installation instructions and usage details in the llm-transparency-tool GitHub repository at github.com/facebookresearch/llm-transparency-tool. The project has 1.3k stars and 104 forks, indicating an active community.
The top alternatives to llm-transparency-tool on Agent Skills Hub include excalidraw-diagram-skill, raptor, chinese-novelist-skill. 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: