bambu-studio-ai
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
OpenClaw Signet
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
SkillHub CLI
skillhub install atlaspa/openclaw-signet打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。
Cryptographic verification for installed skills. Sign skills at install time, verify they haven't been tampered with later.
You install a skill and it works. Days later, a compromised process modifies files inside the skill directory — injecting code, altering behavior, adding exfiltration. All current defenses are heuristic (regex pattern matching). Nothing mathematically verifies that installed code is unchanged.
Generate SHA-256 content hashes for all installed skills and store in trust manifest.
python3 {baseDir}/scripts/signet.py sign --workspace /path/to/workspace
python3 {baseDir}/scripts/signet.py sign openclaw-warden --workspace /path/to/workspace
Compare current skill state against trusted signatures.
python3 {baseDir}/scripts/signet.py verify --workspace /path/to/workspace
python3 {baseDir}/scripts/signet.py list --workspace /path/to/workspace
python3 {baseDir}/scripts/signet.py status --workspace /path/to/workspace
sign computes SHA-256 hashes of every file in each skill directoryverify recomputes hashes and compares against the manifest0 — All skills verified1 — Unsigned skills detected2 — Tampered skills detectedPython standard library only. No pip install. No network calls. Everything runs locally.
Works with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification.
这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。
Cryptographic skill verification for OpenClaw, Claude Code, and any Agent Skills-compatible tool.
Sign installed skills with SHA-256 content hashes. Verify they haven't been tampered with. Detect exactly which files changed.
git clone https://github.com/AtlasPA/openclaw-signet.git
cp -r openclaw-signet ~/.openclaw/workspace/skills/
# Sign all installed skills
python3 scripts/signet.py sign
# Sign a specific skill
python3 scripts/signet.py sign openclaw-warden
# Verify all skills
python3 scripts/signet.py verify
# List signed skills
python3 scripts/signet.py list
# Quick status
python3 scripts/signet.py status
sign: Compute SHA-256 of every file → composite hash → store in manifest
verify: Recompute hashes → compare to manifest → report differences
If any file within a skill is modified, added, or removed, the composite hash changes and verify reports exactly what changed.
|---------|------|-----| | SHA-256 skill signing | Yes | Yes | | Tamper detection | Yes | Yes | | File-level change report | Yes | Yes | | Trust manifest | Yes | Yes | | Reject unsigned skills | - | Yes | | Quarantine tampered skills | - | Yes | | Restore from trusted state | - | Yes | | Pre-install verification | - | Yes |
MIT
# OpenClaw Signet
Cryptographic verification for installed skills. Sign skills at install time, verify they haven't been tampered with later.
## The Problem
You install a skill and it works. Days later, a compromised process modifies files inside the skill directory — injecting code, altering behavior, adding exfiltration. All current defenses are heuristic (regex pattern matching). Nothing mathematically verifies that installed code is unchanged.
## Commands
### Sign Skills
Generate SHA-256 content hashes for all installed skills and store in trust manifest.
```bash
python3 {baseDir}/scripts/signet.py sign --workspace /path/to/workspace
```
### Sign Single Skill
```bash
python3 {baseDir}/scripts/signet.py sign openclaw-warden --workspace /path/to/workspace
```
### Verify Skills
Compare current skill state against trusted signatures.
```bash
python3 {baseDir}/scripts/signet.py verify --workspace /path/to/workspace
```
### List Signed Skills
```bash
python3 {baseDir}/scripts/signet.py list --workspace /path/to/workspace
```
### Quick Status
```bash
python3 {baseDir}/scripts/signet.py status --workspace /path/to/workspace
```
## How It Works
1. `sign` computes SHA-256 hashes of every file in each skill directory
2. A composite hash represents the entire skill state
3. `verify` recomputes hashes and compares against the manifest
4. If any file is modified, added, or removed — the composite hash changes
5. Reports exactly which files changed within each tampered skill
## Exit Codes
- `0` — All skills verified
- `1` — Unsigned skills detected
- `2` — Tampered skills detected
## No External Dependencies
Python standard library only. No pip install. No network calls. Everything runs locally.
## Cross-Platform
Works with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification.# OpenClaw Signet Cryptographic skill verification for [OpenClaw](https://github.com/openclaw/openclaw), [Claude Code](https://docs.anthropic.com/en/docs/claude-code), and any Agent Skills-compatible tool. Sign installed skills with SHA-256 content hashes. Verify they haven't been tampered with. Detect exactly which files changed. ## Install ```bash git clone https://github.com/AtlasPA/openclaw-signet.git cp -r openclaw-signet ~/.openclaw/workspace/skills/ ``` ## Usage ```bash # Sign all installed skills python3 scripts/signet.py sign # Sign a specific skill python3 scripts/signet.py sign openclaw-warden # Verify all skills python3 scripts/signet.py verify # List signed skills python3 scripts/signet.py list # Quick status python3 scripts/signet.py status ``` ## How It Works ``` sign: Compute SHA-256 of every file → composite hash → store in manifest verify: Recompute hashes → compare to manifest → report differences ``` If any file within a skill is modified, added, or removed, the composite hash changes and `verify` reports exactly what changed. |---------|------|-----| | SHA-256 skill signing | Yes | Yes | | Tamper detection | Yes | Yes | | File-level change report | Yes | Yes | | Trust manifest | Yes | Yes | | **Reject unsigned skills** | - | Yes | | **Quarantine tampered skills** | - | Yes | | **Restore from trusted state** | - | Yes | | **Pre-install verification** | - | Yes | ## Requirements - Python 3.8+ - No external dependencies (stdlib only) - Cross-platform: Windows, macOS, Linux ## License MIT
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance