Community研究与数据分析github.com

Akshay7273/skill-advisories

Open advisory database for AI agent skills, plugins, and MCP servers — machine-readable threat data for the agent ecosystem.

skill-advisories 是什么?

skill-advisories is a Claude Code agent skill that open advisory database for AI agent skills, plugins, and MCP servers — machine-readable threat data for the agent ecosystem.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add Akshay7273/skill-advisories

Installed? Explore more 研究与数据分析 skills: obra/superpowers, affaan-m/quarkus-verification, affaan-m/uspto-database · View all 6 →

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Skill advisory check

Use this skill before installing or updating an untrusted OpenClaw/ClawHub skill. Ask for the exact registry identity and version when the request is ambiguous.

Run from this skill directory:

node scripts/check-artifact.mjs <skill-name> --version <version>

Exit code 0 means no matching advisory is currently known; it does not prove the artifact is safe. Exit code 1 means policy found a known advisory. Exit code 2 means the check could not complete and installation must stop.

Report the SKA identifier, severity, summary, and evidence URLs to the user. Do not proceed automatically after a warning or operational failure.

相关技能