元安全 yotta-agent-hardening

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

as observed 2026-09-03T07:20:35.503Z

Want to know when this changes? Sign in with an email address and we will tell you. Free, no card, watch up to 5.

Identifier: yotta-agent-hardening
Source: ClawHub
Version observed: 0.2.5
Source repository: not published
Repository observation: No source repository listed
First observed here: 2026-08-29T23:02:09.653Z
Observations recorded: 3
Installs (reported upstream): 0
Weekly downloads (upstream): 166

Observation history

2026-09-03T07:20:35.503Z

Fields that differed: changelog latestVersion topics

Field	Before	After
`changelog`	"yotta-agent-hardening v0.2.4\n\n- Updated references/report-template.md to refine hardening report templates and content structure.\n- Minor text and markdown improvements in	"- 移除了 skill-card.md 文件，不再包含该说明文档。\n- 其余功能、用法和守则均保持不变。"
`latestVersion`	"0.2.4"	"0.2.5"
`topics`	["security"]	["安全体检","工具调用安全","提示注入","数据隔离","智能体安全"]

2026-08-31T05:56:02.339Z

Fields that differed: changelog latestVersion

Field	Before	After
`changelog`	"yotta-agent-hardening 0.1.0 初始发布\n\n- 发布元安全工具，为 AI 智能体 / Agent 提供环境安全体检与加固建议\n- 三域扫描：提示注入防护、工具调用边界、数据隔离\n- 支持扫描已安装 skills、MCP 服务器、工具描述与权限配置，输出合规性报告\n- 提供可执行防御守则生成与文件校验，扫描留痕默认	"yotta-agent-hardening v0.2.4\n\n- Updated references/report-template.md to refine hardening report templates and content structure.\n- Minor text and markdown improvements in
`latestVersion`	"0.1.0"	"0.2.4"

Correction

If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.