LLMs-from-scratch
Repository: LLMs-from-scratch
Author: rasbt · Source status: Clear source
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Score basis:Clear source · Risk needs review · Universal
Repository: clawmanager-openclaw-image
Author: Yuan-lab-LLM·Source status: Clear source
GitHub repository Yuan-lab-LLM/clawmanager-openclaw-image; metadata recovered from GitHub Search API.
Score basis:Clear source · Risk needs review · Universal
Trust level
63 · Review first
Usable, but inspect source, install method, and risk hints before adoption.
Risk decision
Review required
metadata-only
Install readiness
script-backed · copy-only command
SkillTrust only shows install guidance and copy actions; it never executes installs.
Before you install
Review source, permissions, and execution risk first, then alternatives. Scores prioritize review; they do not replace manual judgment.
Review weakest dimensions and next actions before copying commands.
Evidence or risk signals are incomplete; compare alternatives first.
Audit grade
C · Review first
Execution risk
High
Evidence confidence
65%
SAS-v2.1 radar
SAS-v2.1
Audit grade
C · Review first
Execution risk
High
Top threats
unexpected code execution, data exfiltration
Control gaps
missing license, broad permissions
Evidence confidence
65%
Repository
Yuan-lab-LLM/clawmanager-openclaw-image
Author
Yuan-lab-LLM
Community signal
4 stars · 7 forks
Last updated
2026-04-08
Primary source
Yuan-lab-LLM/clawmanager-openclaw-image
Source status
Clear source
Install method
script-backed
Command & code execution
34Focus: Whether it runs commands or scripts
Next action: Manually confirm command-running skills in an isolated directory.
High-risk action confirmation
38Focus: Whether destructive or external actions require confirmation
Next action: Avoid directly installing high-risk skills without confirmation controls.
Network & data egress
43Focus: Whether it may send data out
Next action: If unsure, restrict network access or allow only known domains.
Supported tools can change install steps; Universal entries need source review.
Explicitly supported
Candidate support (inferred)
Candidate tools are inferred signals, not official compatibility certifications.
git clone https://github.com/Yuan-lab-LLM/clawmanager-openclaw-image.gitmetadata-only
Review source and permissions before copying install commands.
Evidence or risk signals are incomplete; compare alternatives first.
Focus: Who published it and whether it is traceable
Next action: Review repository, author, and README first; do not install directly when source is pending.
Focus: Whether install steps can be reviewed
Next action: Prefer candidates with install docs and repository evidence.
Focus: Whether tool descriptions may hide instructions
Next action: Read README, rules, and tool descriptions before install.
Focus: What it can access
Next action: Grant only task-required permissions and prefer Ask/manual confirmation.
Focus: Whether it runs commands or scripts
Next action: Manually confirm command-running skills in an isolated directory.
Focus: Whether file reads/writes can escape scope
Next action: Check working directory and file access scope before running.
Focus: Whether it may send data out
Next action: If unsure, restrict network access or allow only known domains.
Focus: Whether it handles tokens, private keys, or agent identity
Next action: Do not provide long-lived tokens or private keys to source-pending skills.
Focus: Whether external content can steer behavior
Next action: For browser/RAG/rules skills, review permissions and confirmation controls first.
Focus: Whether memory or retrieved context can be poisoned
Next action: Try RAG/memory skills in a low-privilege environment first.
Focus: Whether external tools and MCP access are clearly bounded
Next action: Confirm which external tools it will connect to before install, and start with the smallest possible set.
Focus: Whether destructive or external actions require confirmation
Next action: Avoid directly installing high-risk skills without confirmation controls.
Focus: How far impact can spread when something goes wrong
Next action: If unsure, test in an isolated project first.
Focus: Whether actions can be traced
Next action: Prefer candidates with logs or previews.
Focus: Whether it is maintained and reusable
Next action: Check license and maintenance before organizational use.
Usable, but inspect source, install method, and risk hints before adoption.
Phase 1 only shows installation-aware, source-backed signals. SkillTrust does not execute install scripts for users.
Risk factors
metadata-only
Permission hints
repository clone
Why related: Same task category, Keyword overlap...
Why related: Same task category, Keyword overlap, Similar install method
Repository: llm-app
Author: pathwaycom · Source status: Clear source
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data.
Score basis:Clear source · Risk needs review · Universal
Why related: Same task category, Keyword overlap...
Why related: Same task category, Keyword overlap, Similar install method
Repository: one-api
Author: songquanpeng · Source status: Clear source
LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型,统一 API 适配,可用于 key 管理与二次分发。单可执行文件,提供 Docker 镜像,一键部署,开箱即用。LLM API management & key redistribution syst…
Score basis:Clear source · Risk needs review · Universal
Why related: Same task category, Keyword overlap...
Why related: Same task category, Keyword overlap, Similar install method
Repository: andrej-karpathy-skills
Author: forrestchang · Source status: Clear source
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Score basis:Clear source · Risk needs review · Universal
Why related: Same task category, Keyword overlap...
Why related: Same task category, Keyword overlap, Similar install method
Repository: open-webui
Author: open-webui · Source status: Clear source
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Score basis:Clear source · Risk needs review · Universal
Why related: Same task category, Keyword overlap...
Why related: Same task category, Keyword overlap, Similar install method
Repository: llama.cpp
Author: ggml-org · Source status: Clear source
LLM inference in C/C++
Score basis:Clear source · Risk needs review · Universal
Why related: Same task category, Keyword overlap...
Why related: Same task category, Keyword overlap, Similar install method
Repository: ClawManager
Author: Yuan-lab-LLM · Source status: Clear source
A Kubernetes-first control plane for managing OpenClaw and Linux desktop runtimes at team and cluster scale.
Score basis:Clear source · Risk needs review · Universal