lgd-skillgate
面向 AI Agent Skill 的离线静态扫描器:读 SKILL.md 与随附脚本,输出 Trust Score、grade、findings(含稳定规则 ID 与 文件:行号)。纯标准库、无网络、无遥测。
安装(本地,不联网 PyPI)
python -m venv .venv
# Windows: .venv\Scripts\activate Linux/macOS: source .venv/bin/activate
pip install .
三条命令(陌生人可照抄)
# 1) 扫描一个恶意示例,期望 grade D、trust_score 40、命中 MD001 + CR010、exit 1
lgd-skillgate scan examples/malicious --format json
# 2) 扫描一个良性示例,期望 grade A、findings 0、exit 0
lgd-skillgate scan examples/benign --format json
# 3) 终端可读报告
lgd-skillgate scan examples/malicious
CI 用法:lgd-skillgate scan ./skills --fail-under 70,低于阈值即 exit 1。
能核什么(不要信文字,信输出)
- 规则可对位:每条 finding 带规则 ID(如
MD005、SH004),可在源码里按文件:行号直接定位。 - 构建可识别:
rule_version随规则增长递增;--format json里含本次判定所用版本。 - 判定可复跑:同一目录重复扫描结果稳定;无随机、无网络。
- 红队数字可自算:仓库另附独立复算脚本,只读逐样本
flagged字段重算 TP/FP/TN/FN,不调用扫描器。
明确不能做
- 不做动态沙箱执行,不执行被扫描代码。
- 不检测模型层提示注入的语义变体(只做模式与 AST/JS 静态规则)。
- 不提供"已获第三方认证"或"行业最强"类结论;本包只有 0 外部运行、0 外部评审。
许可
见 LICENSE(随仓文件原样保留,未改动署名)。
Metadata
Release files for lgd-skillgate 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| lgd_skillgate-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for lgd_skillgate-0.1.0-py3-none-any.whl |
Release files / lgd_skillgate-0.1.0-py3-none-any.whl
| Download URL | lgd_skillgate-0.1.0-py3-none-any.whl |
|---|---|
| Size | 35.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
db9b2300cc0b43a53897bb088461e662b4fbf97ca18197847360bc77cbf8d77f
|
|
BLAKE2b-256 checksum How to use checksums |
2b23ac53a8c62456ae3b8914093577d2cd4257e0db5632d3e25044d316f04ccc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.18
|
Security for lgd-skillgate 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.