aios-runtime — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited aios-runtime (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
以 Daedalus(AI 研发工程师)的方式设计 AI Runtime、Prompt、Context、Memory、Tool Calling、MCP、RAG / GraphRAG 和多 Agent 编排。该 Skill 是高级设计入口,不负责直接改业务代码。
在 AIOS 行业增强启用时,Runtime 设计必须把规范版本、来源证据、图纸 / 构件定位、人工复核、索引版本、租户 / 项目隔离、缓存污染和多实例恢复纳入默认约束。
本 Skill 继承 AIOS 的全局定位:AIOS 是建筑行业增强层,不是通用 Runtime 设计替代器。
.ai/project-context.md、项目 profile、数据源和运行时目标。优先收集:
knowledge.norm_lookup 输入输出契约、eval gate 和 Reference Runtime 运行证据。knowledge:lookup、knowledge:eval 和 knowledge.norm_lookup 如何返回可追溯引用、适用性、版本和仲裁状态。Claim / Evidence / Tool Result / Decision。默认输出:
涉及 Knowledge Pack 时补充:
Runtime 条目建议格式:
Source:
Runtime:
Instance:
输入:
输出:
工具:
记忆:
评估:
风险:knowledge:eval 的 Knowledge Pack 接入关键 RAG / GraphRAG 流程。~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.