@yottameta/yotta-agent-hardening 0.2.3 → 0.2.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md
CHANGED
|
@@ -1,8 +1,16 @@
|
|
|
1
1
|
# 更新日志
|
|
2
2
|
|
|
3
|
+
## v0.2.6 (2026-09-19)
|
|
4
|
+
|
|
5
|
+
版本对齐维护：修复历史发布元数据与包内版本不一致；无功能变更。
|
|
6
|
+
|
|
7
|
+
## v0.2.4 (2026-08-30)
|
|
8
|
+
|
|
9
|
+
表述修正：统一对外表述。
|
|
10
|
+
|
|
3
11
|
## v0.2.3 (2026-08-30)
|
|
4
12
|
|
|
5
|
-
表述修正：统一为「MIT
|
|
13
|
+
表述修正：统一为「MIT 开源发布、能力开放」的对外表述。
|
|
6
14
|
|
|
7
15
|
## v0.2.2 (2026-08-30)
|
|
8
16
|
|
package/SKILL.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: yotta-agent-hardening
|
|
3
|
-
version: 0.2.
|
|
3
|
+
version: 0.2.6
|
|
4
4
|
description: 元安全 —— 给 AI 智能体 / Agent 技能自身做「体检 + 加固建议」：按 提示注入防护 / 工具调用边界 / 数据隔离 三域，对安装的 skills、MCP 服务器、工具描述、权限与数据读取面做配置面静态加固扫描，输出加固报告与可执行防御守则（零依赖 Python 3.8+，扫描只读、敏感读取检测默认开启、报告用「类」表述、每次扫描默认留痕）。触发：用户要求给智能体或技能环境做安全体检 / 加固、检查 MCP 服务器或技能是否可信、排查提示注入 / 越权 / 数据泄露风险、想了解装了一堆技能后的整体暴露面；或用户说 元安全 / 加固 / 安全体检 / 体检 / hardening / 扫一下我的技能 / 检查 MCP / 防御守则 / guardrails 等。边界（Do NOT trigger）：不产出可复制注入串 / 攻击 payload；只扫描用户自有、有权检查的目录与配置，不扫描无权访问的环境；不做运行时拦截（那是元盾）；不做单个技能装前审核（那是元审 / 元信）；不替代人工安全审计与最终决策。
|
|
5
5
|
license: MIT
|
|
6
6
|
---
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@yottameta/yotta-agent-hardening",
|
|
3
|
-
"version": "0.2.
|
|
3
|
+
"version": "0.2.6",
|
|
4
4
|
"description": "YuanSafe (元安全) — a defensive AI-agent hardening skill: static configuration-facing hardening scan of an agent's own runtime (installed skills, MCP servers, tool descriptions, permissions and data surfaces) across three domains — prompt-injection defense / tool-call boundaries / data isolation — producing a hardening report and enforceable defense guardrails, with zero-dependency Python 3.8+, read-only scanning, sensitive-read detection on by default, \"class\" phrasing in reports (no copy-paste injection strings) and an audit trail on every scan. Triggers: user asks for a security check / hardening of an agent or skill environment, whether MCP servers or skills are trustworthy, prompt-injection / over-privilege / data-leak risk investigation, or the overall exposure after installing many skills. Boundaries: no executable injection strings or attack payloads; scans only directories and configs the user owns or is authorized to inspect; no runtime interception (that is yotta-guardian); no per-skill pre-install review (that is yotta-vetter / yotta-verify); human review and final decisions are not replaced.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"keywords": [
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# 防御守则模板（guardrails template）
|
|
2
2
|
|
|
3
|
-
> 本文件 = `rules` 命令的当前输出（生成工具：yotta-agent-hardening v0.2.
|
|
3
|
+
> 本文件 = `rules` 命令的当前输出（生成工具：yotta-agent-hardening v0.2.6，格式版本 1）。
|
|
4
4
|
> 权威来源永远是 CLI：`python3 scripts/yotta_agent_hardening.py rules`，版本升级后以命令输出为准。
|
|
5
5
|
|
|
6
6
|
## 用途
|
|
@@ -16,7 +16,7 @@
|
|
|
16
16
|
|
|
17
17
|
```markdown
|
|
18
18
|
# 智能体加固守则（元安全 · yotta-agent-hardening）
|
|
19
|
-
> 生成工具：yotta-agent-hardening v0.2.
|
|
19
|
+
> 生成工具：yotta-agent-hardening v0.2.6；格式版本 1；覆盖三域（提示注入防护 / 工具调用边界 / 数据隔离）。
|
|
20
20
|
> 用法：放入智能体运行时目录（如 .yotta-hardening/GUARDRAILS.md），让智能体每次会话读取执行。
|
|
21
21
|
|
|
22
22
|
## 域 1：Prompt injection 防护
|