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
- When the user questions or follows up on what an agent just did and asks to "check the ledger".
- When suspected risk behavior is detected: unauthorized access, unapproved execution, "no registration", or "failed gate".
- When reporting AI-service compliance to management and needing a fully traceable behavior ledger as evidence.
- When the user explicitly uses trigger words (e.g. "behavior trace", "audit log") to start a review.
Usage
Natural-language calls are supported, as well as precise command-line execution; the underlying script is trace_audit.py. Configurable parameters: -t/--time-range (query window), -f/--format (json/text output), -v/--violation-flag (force-flag boundary-crossing actions). Without the command line, just say "audit the AI behavior just now" and the call protocol matches automatically.
Process
- The user issues an instruction or natural-language question containing audit intent.
- The system parses context, identifies the
trace_auditscript, and loads the local log cache. - The script reads core fields: timestamp, actor, action, and object.
- Per the LGD Three Laws, verify whether each operation has a "gate" permission record.
- Auto-filter boundary-crossing actions that failed the gate, and build a full timeline plus violation list.
- Return an audit conclusion with the evidence chain and follow-up compliance advice.
Evidence & safety statement
- Evidence: TBD (no evaluation/badge link yet; fill in the real link here once produced).
- Version: 1.0.1
- Safety: No independent security scan has been done (TBD); the conclusion is pending. No endorsement is given until it is completed.
中文
何时用
- 当用户质疑或追问 Agent 刚完成的具体操作及其结果,要求“查账”时。
- 当检测到疑似 AI 存在越权访问、未授权执行等“无籍”或“过闸失败”风险行为时。
- 当需要向管理层汇报 AI 服务合规性,需提供全程可追溯的行为账本证据时。
- 当用户在对话中显式使用触发词(如“行为留痕”、“审计日志”)发起核查请求时。
用法
支持自然语言直接调用或命令行精确执行,底层脚本文件位于 __pycache__/trace_audit.py。可配置参数:-t/--time-range (设定日志查询时间窗口);-f/--format (指定输出格式为 json/text);-v/--violation-flag (强制标记越界操作)。若无需命令行,直接描述“帮我审计一下刚才的 AI 行为”即可自动匹配调用协议。
流程
- 用户发起包含审计意图的指令或自然语言提问。
- 系统解析上下文,识别
trace_audit脚本并加载本地日志缓存。 - 执行脚本读取时间戳、执行者、动作及对象等核心字段。
- 依据 LGD 三律标准校验每笔操作是否具备“过闸”权限记录。
- 自动筛选未过闸的越界行为,构建完整的时间线与违规清单。
- 向用户返回含证据链的审计结论与后续合规建议。
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:1.0.0
- 安全:未做独立安全扫描(TBD),结论待补;补全前不作推荐背书。
