prompt-injection-shield

提示注入防护 — 在不可信内容进上下文之前先扫描：中英双语文式库（忽略指令/角色劫持/越狱/DAN/索要系统提示）+ 启发式 + 沙箱规则，输出风险分·命中规则·处置建议。

凡自治之物 · LGD 治理学 · 创造术家族 ｜ 评测协议：skill-quality-gate

English

When to use

1. Before data ingestion: when web pages, emails, tool returns, or uploaded documents are about to be fed to the AI, pre-scan before they enter context.
2. Prevent instruction hijack: detect "ignore previous instructions", "you are a new AI", jailbreak or system-prompt-leak attempts.
3. As a pre-stage to release-gate, combining desens-scan for double-checking so untrusted content cannot pollute context.

How to use

• Run python scripts/prompt_injection_scan.py.
• Pass the text to scan via --input and set the scan mode via --mode safe/aggressive.
• Output includes risk score, matched rules, and disposition advice; read the returned JSON for downstream decisions.

Workflow

1. Submit content to the bilingual pattern + heuristic scanner.
2. The engine identifies jailbreak, DAN, role hijack, and system-prompt-leak traits and checks sandbox rules.
3. Score the overall risk; record matched rules and decide whether to trigger desensitization or blocking.
4. Produce a disposition (drop/isolate/sandbox), reusing desens-scan and release-gate logic.
5. The front-end acts on the score: block, isolate, or run in a safe sandbox.

Evidence & safety

• Evidence: TBD; Version: 1.0.1; Security: no independent scan (TBD).

中文

提示注入防护

何时用

1. 数据接入前扫描：网页抓取、邮件、工具返回值或上传文档喂给 AI 前做安全预审。
2. 防止指令劫持：检测「忽略之前指令」「你是新 AI」等触发词，防越狱或泄露系统提示。
3. 作为 release-gate 前置环节，结合 desens-scan 双重校验，防不可信内容污染上下文。

用法

• 运行 python scripts/prompt_injection_scan.py。
• --input 传入待扫描文本，--mode safe/aggressive 指定模式。
• 输出含风险分、命中规则详情与处置建议，可读返回 JSON 做后续决策。

流程

提交内容到双语文式库+启发式扫描入口 → 识别越狱/DAN/角色劫持/系统提示泄露特征并关联沙箱规则 → 计算风险分并记录命中规则 → 生成处置建议（丢弃/隔离/沙箱）→ 前端按分拦截/隔离/沙箱运行。

证据与安全声明

• 证据：TBD；版本：1.0.1；安全：未做独立安全扫描（TBD）。