📦 EDA Spec2GDS — 一键流片
v1.0.1基于OpenClaw技能、工作区文件与CLI工具，驱动开源EDA流程，将硬件规格直接生成GDS版图，实现从设计到流片的自动化。
0· 140·0 当前·0 累计
by 下载技能包
最后更新
2026/4/19
安全扫描
OpenClaw
安全
high confidenceNULL
评估建议
This skill appears to be what it claims: an artifact-first EDA flow with optional setup scripts. Before running any install/bootstrap scripts: 1) review scripts/install_ubuntu_24_mvp.sh and scripts/bootstrap_eda_demo.sh line-by-line; 2) run installs only in an isolated VM/container or a disposable workstation (do NOT run on production); 3) be aware the installer adds you to the docker group and enables the Docker daemon — membership in the docker group effectively grants root-equivalent capabili...详细分析 ▾
✓ 用途与能力
The name/description (spec → RTL → synthesis → OpenLane → GDS) aligns with the declared requirements: yosys, iverilog/vvp, docker, python3 and multiple scripts that implement the workflow. Declared permissions (sudo access for installs, docker_group) match the install script behavior. There are no unrelated credentials, binaries, or unexpected external services requested.
ℹ 指令范围
SKILL.md and the scripts focus on file-based EDA workflows and stepwise execution. The runtime instructions do include optional system-modifying steps (install_ubuntu_24_mvp.sh and bootstrap_eda_demo.sh) which perform package installs, start Docker, create a Python venv, and pull images. Those operations are within the skill's claimed scope but expand the agent's authority (need sudo, modify groups, network downloads). The documentation repeatedly warns to only run installs in an isolated environment.
ℹ 安装机制
There is no automatic install spec but the repository includes install scripts that run apt-get, pip install, and docker pull (Docker Hub). These use well-known package sources (apt, PyPI, Docker Hub) rather than arbitrary shorteners or personal servers, which is expected for this use case. Supply-chain risk remains (untrusted packages/images), so the scripts should be reviewed and images/pip pins verified before use.
✓ 凭证需求
The skill requests no environment variables or secret credentials. The only environment/config changes are typical for toolchain setup: creating a Python venv (~$HOME/.venvs/openlane) and modifying docker group membership. The code does not attempt to read or exfiltrate secrets or access unrelated system config paths beyond typical install locations and the skill workspace.
⚠ 持久化与权限
The optional installation scripts enable and start the Docker daemon and add the user to the docker group (usermod -aG docker), which grants powerful privileges and is a common escalation vector. The scripts also modify system packages (/usr/bin, services) via sudo. These are expected for running OpenLane but are high-privilege actions — the skill documents and warns about them, but users should treat the install steps as potentially risky and run them only in isolated environments.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.12026/3/20
NULL
● 可疑
安装命令
点击复制官方npx clawhub@latest install eda-spec2gds
镜像加速npx clawhub@latest install eda-spec2gds --registry https://cn.longxiaskill.com