Shared audit integrity framework for all AppSec agents — enforces output quality, intellectual honesty, and continuous improvement through anti-rationalization guards, self-critique loops, retry protocols, non-negotiable behaviors, self-reflection quality gates (1-10 scoring, ≥8 threshold), and a self-learning system with lesson/memory governance for security analysis agents.
GitHub 来源
以下内容派生自固定 commit；社区导读与原始来源分开保存。
安全检测
平台只做静态检测，不运行 Skill。检测未发现不等于不存在风险；采用前请核对能力、来源与版本。
SKILL_LICENSE_MISSING
SKILL.md:— · 不可变清单
整包摘要: c3f58d4adf5f11dcf055e90a0afe3074f32c3fdd237b77e4b8ab49887a4529a7
| 路径 | 类型 | 大小 | SHA-256 |
|---|---|---|---|
| SKILL.md | text | 3,343 B | 53b66285… |
| references/clarification-protocol.md | text | 971 B | bfa0c8ad… |
| references/self-learning-system.md | text | 2,330 B | 7bc67558… |
| references/self-critique-loop.md | text | 2,592 B | 2f815ddc… |
| references/anti-rationalization-guard.md | text | 4,044 B | e9760aa3… |
| references/retry-protocol.md | text | 560 B | 4dbfd762… |
| references/self-reflection-quality-gate.md | text | 2,438 B | 12e17024… |
| references/non-negotiable-behaviors.md | text | 1,469 B | adda8b88… |
版本历史
版本绑定社区
每条反馈都绑定具体版本，不提供脱离 Skill 的泛论坛帖子。
这个版本还没有社区反馈。