安全审计专家

分享海报

@user_ee0c0d25/skill-analysis

装 Skill 前，先过一遍安检 —— 纯本地 · 零外联 · 零第三方依赖，代码不出你的机器。①【一句话结论】BLOCK / NEED_REVIEW / PASS 准入判定 + 0-100 风险评分 + A-F 等级与发布建议。②【按需守护】显式命令一键扫描全部已装 Skill + 变动监控（watchdog），新装 Skill 静默体检（不常驻、不注册任何钩子）。③【深度对抗】多层混淆解码、污点数据流、Unicode 走私指令解码、反序列化 RCE、条件触发注入、沙箱动态取证。④【情报驱动】勒索病毒、提示注入、MCP 工具投毒、供应链投毒、金融欺诈诱导、身份自改写持久化、Agent 记忆投毒（ASI06）。⑤【工程化】跨平台批量扫描、CI 门禁、SARIF/SBOM/JSON 导出。⑥【可自证可信】无自动更新、发布者签名锚 + SHA-256 + 一键签名核验 + 独立复验。\n\nEN: Run a security check before installing any Skill -- 100% local, zero network calls, zero third-party dependencies; your code never leaves your machine. (1) One-shot verdict: BLOCK / NEED_REVIEW / PASS with a 0-100 risk score, A-F grading and publishing advice. (2) On-demand guard: one-command scan of all installed Skills plus a change monitor (watchdog); silent health checks for newly installed Skills (nothing resident, no hooks registered). (3) Deep adversarial detection: multi-layer de-obfuscation, taint data-flow, Unicode smuggled-instruction decoding, deserialization RCE, conditional trigger injection, sandboxed dynamic forensics. (4) Intelligence-driven rules: ransomware, prompt injection, MCP tool poisoning, supply-chain poisoning, financial-fraud inducement, identity self-rewrite persistence, agent memory poisoning (ASI06). (5) Engineering: cross-platform batch scanning, CI gate, SARIF/SBOM/JSON export. (6) Self-verifiable trust: no auto-update, publisher signature anchor + SHA-256 + one-command signature verification + independent re-validation.