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
- Before publishing or sharing any prompt that may contain sensitive information, run the final security audit.
- When you need to verify whether internal system configurations contain secrets, passwords, PII or internal paths.
- When deep inspection of third-party input or custom rules is required — especially checking for self-leak backdoor risks.
Usage
- Script:
python prompt_leak_scanner.py - Arguments:
--input: required; the prompt / system-prompt text to scan.--extra: optional; custom sensitive-word list to extend detection (--extra "word1,word2").--check_cache: optional; whether to also scan auxiliary logic in__pycache__.
- Output: returns a risk-level code rc (0 = no risk, safe to publish; 1 = leak found, must block).
Workflow
- The caller prepares the prompt text under review and the configuration parameters.
- Pass the command through the skill interface to run
prompt_leak_scanner.pyfor analysis. - The system scans keywords, paths and backdoor-command patterns in memory per the script logic.
- The tool parses the risk level and emits the corresponding return code (rc=1) or a no-risk confirmation.
- If
rc=1is detected, the publish flow is blocked automatically and a block signal is sent upstream. - Only after risk is confirmed as
rc=0may subsequent data-sharing operations proceed.
Evidence & safety statement
- Evidence: TBD (no evaluation / badge link yet; update here once produced)
- Version: 1.0.1
- Safety: no independent security scan has been performed (TBD); the conclusion is pending and no endorsement is given until it is completed.
中文
何时用
- 在发布或共享任何包含潜在敏感信息的提示词(Prompt)之前,执行最终安全审计。
- 当需要验证系统内部配置是否存在密钥、口令、个人可识别信息(PII)或内部路径时。
- 针对第三方输入内容或自定义规则进行深度检测,特别是检查自我泄漏后门风险。
用法
- 执行脚本:
python prompt_leak_scanner.py - 命令参数:
--input: 必须,提供待扫描的 Prompt/System Prompt 内容文本。--extra: 可选,提供自定义敏感词组用于扩展检测规则(支持--extra "word1,word2")。--check_cache: 可选,是否关联扫描__pycache__中的辅助脚本逻辑进行验证。
- 输出说明: 返回风险等级码 rc(0 表示无风险可发布,1 表示存在泄漏需阻断)。
流程
- 调用方准备待审核的提示文本及相关配置参数。
- 通过技能接口传入命令执行
prompt_leak_scanner.py进行逻辑分析。 - 系统根据脚本逻辑在内存中扫描关键词、路径及后门指令模式。
- 工具解析风险等级并生成对应的返回码(rc=1)或无风险确认。
- 若检测到
rc=1,自动拦截发布流程并向上游发送阻断信号。 - 仅在确认风险为
rc=0后,允许继续进行后续的数据共享操作。
证据与安全声明
- 证据:TBD(暂无评测/徽章链接;产生后在此更新实际链接)
- 版本:1.0.1
- 安全:未做独立安全扫描(TBD),结论待补;补全前不作推荐背书。
