Summary
- AI 系统身份与权限安全测试方法论。当目标系统涉及 Agent 身份认证、多 Agent 权限管理、
- 角色设定安全、会话管理、或 MCP/API 凭据管控时触发。
- 覆盖: 角色逃逸(假定场景/假定角色/遗忘法/目标劫持)、权限失控(Action 越权/MCP 未授权资源获取)、
- 多 Agent…
wgpsec/aboutsecurity
AI 系统身份与权限安全测试方法论。当目标系统涉及 Agent 身份认证、多 Agent 权限管理、 角色设定安全、会话管理、或 MCP/API 凭据管控时触发。 覆盖: 角色逃逸(假定场景/假定角色/遗忘法/目标劫持)、权限失控(Action 越权/MCP 未授权资源获取)、 多 Agent 身份伪造、会话劫持、凭据泄露与滥用。
npx skills add https://github.com/wgpsec/aboutsecurity
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Use Link CLI's identity commands when a service requests a Link Agent Attestation Token (AAT) o…
393 installsKnow Your Agent (KYA). Billions decentralized identity for agents. Link agents to human identit…
8.2K installsDetect and review name/content drift in code using `indexion identity audit`, then plan verifie…
4.9K installsDesign and audit the lived culture of a technical event - the register (hacker, corporate, desi…
205 installsAdd authentication and user management to a Netlify site with @netlify/identity — signup/login/…
24 installsERC-8004 on-chain Agent identity on XLayer: register / create / update / activate / deactivate …
2.3K installsOther skills from wgpsec/aboutsecurity · top by installs.
npx skills add https://github.com/wgpsec/aboutsecurity
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
master