Install
openclaw skills install @zhaoxinghua09-cell/prompt-injection-guardStatic scan for 8 threat categories (prompt injection, hardcoded secrets, destructive commands, exfiltration, crypto-mining, privesc, persistence, obfuscation); outputs risk report + SAFE badge, fail-closed, zero-dependency. 八类威胁静态扫描(提示注入/硬编码密钥/破坏性命令/数据外泄等),输出风险报告 + SAFE 徽章,fail-closed 退出码,零依赖。
openclaw skills install @zhaoxinghua09-cell/prompt-injection-guard凡自治之物 · LGD 治理学 · 创造术家族 | 评测协议:skill-quality-gate
python scripts/prompt_guard.py <file|text> [--json] [--badge out.svg]
prompt_guard.py <file|text> [--json] [--badge out.svg].--badge out.svg emits an LGD SAFE SVG; FAIL → exit 1 (fail-closed).python scripts/prompt_guard.py <file|text> [--json] [--badge out.svg]
python scripts/prompt_guard.py <file|text> [--json] [--badge out.svg]。--badge out.svg 时生成 LGD SAFE SVG;FAIL 时退出码为 1(fail-closed)。这些是用户真实会说的话(中 / 英对照),命中任一即应加载本技能:
Trigger when the user says any of the above, in Chinese or English.
This skill is one door of the LGD ecosystem — every entry below is publicly reachable. 本技能是 LGD 生态 的一个入口,下列地址均对公网可达。
Tell your AI assistant: "Find me an LGD skill that can " — the hub lists every published skill with a one-line purpose. 跟你的 AI 助手说一句「去 LGD 生态超市找能……的技能」,总入口按用途列全了所有已发布技能。