BD release-gate-audit
发布前放行门禁：判定一个产物能否公开发布。与常规密钥扫描器的根本区别是判定对象——它以 git 已追踪内容 + 全部提交历史构成的「公开面」为准，而不是 ls 看到的工作目录，因此既不会把本地文件误报成泄露，也不会漏掉当前已删除但仍存在于旧 commit 中的凭证。四类威胁分离处置（凭证需吊销 / 雇主内部信息需泛化 / PII 兼可移植性缺陷 / 本地专属产物需停止追踪），并提供整改闭环的机器验证（前后报告对比 + 历史残留核查 + 强制吊销清单），避免『我觉得修好了』。内部词表一律外部注入，工具自身可开源。适用场景：开源仓库首次公开、分享 skill/文章/demo/slide、代码外发、合规审查、发版前放行、以及排查『内部信息是否泄露到公开产物』。
发布前放行门禁：判定一个产物能否公开发布。与常规密钥扫描器的根本区别是判定对象——它以 git 已追踪内容 + 全部提交历史构成的「公开面」为准，而不是 ls 看到的工作目录，因此既不会把本地文件误报成泄露，也不会漏掉当前已删除但仍存在于旧 commit 中的凭证。四类威胁分离处置（凭证需吊销 /…
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-aws-keyassets/self-audit-baseline.json:4AWS access key ID (placeholder value)"_review_note": "AKIA…PLE 为 AWS 官方文档固定示例串；变量插值语法非字面密码；apiKey 单测假值为说明用例；MYCO-/INT- 为词表语法示例；RealPass/10.0.3.14 为虚构教学样例；「司内」「公司内部」为设计原则论述用词。",
placeholder -
low Secrets in code
secret-aws-keyreferences/false-positive-playbook.md:29AWS access key ID (placeholder value)| 厂商官方文档里的示例串| **误报**。如 AWS 的 `AKIA…PLE`（这串就是 AWS 文档专用示例） |
placeholder -
low Secrets in code
secret-aws-keyreferences/false-positive-playbook.md:71AWS access key ID (placeholder value)| `AKIA…PLE` | AWS 官方文档的固定示例 Access Key |
placeholder -
low Secrets in code
secret-aws-keyreferences/false-positive-playbook.md:144AWS access key ID (placeholder value)| 1 | `test/reda…:20` | `AKIA…PLE` | 误报 | AWS 官方文档示例串，且位于脱敏功能的单测中 |
placeholder -
low Secrets in code
secret-aws-keyscripts/release_gate.py:463AWS access key ID (placeholder value)print(" （如 AKIA…PLE）、localhost 测试凭证、${VAR} 插值都是常见误报。")placeholder
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en"
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1738 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 331: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.