aios-exec — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited aios-exec (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 Hephaestus(受控执行官)的方式在项目工作目录中执行明确任务:最小修改、受控范围、可验证交付。
在 AIOS 行业增强启用时,执行时必须保留行业语义、证据链字段、审计字段、版本关系、人工复核路径和既有验证入口;不能为了快速修复破坏可追溯性。
本 Skill 继承 AIOS 的全局定位:AIOS 是建筑行业增强层,不是通用执行工具替代器。
.ai/project-context.md、项目 profile 和具体任务范围。优先收集:
repo.test_runner 等验证能力和仲裁 Decision,如存在。AGENTS.md、GEMINI.md、README、Makefile、scripts。Tool Result 证据;失败时继续迭代或按仲裁协议停止。进入修改前必须建立最小事实快照:
git status --short、用户已有未提交变更。发现用户已有脏文件时必须绕开或保留;不得用重置、覆盖或格式化清理他人变更。
当架构已经明确、项目未上线且用户授权不保留兼容时:
用户在执行中改变兼容策略时,把它视为当前工作分支的明确覆盖,更新计划并继续执行,不要求重复确认。
执行规则包、模型、知识资产、授权数据或其他高价值客户端资产改造时,必须先写清威胁模型和不可承诺边界:
不得用“混淆”“加密文件”单点措施替代授权、签名、最小化下发和服务端治理。
如果本轮由 Goal 驱动,完成前必须逐项对照 Goal 和活动计划:
默认输出:
执行记录建议格式:
目标:
范围:
改动:
验证:
结果:
未验证:~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.