BD code-review-and-quality
多维度质量审查，覆盖五轴（正确性/可读性/架构/安全/性能）+ Agent Skill安全审计（NVIDIA SkillSpector 16类漏洞模式 + Palo Alto BIV声明-行为完整性验证 + MCP Server安全审计）。 26%的Agent技能含漏洞，5.2%含恶意代码，80%存在声明与行为偏差——安全轴升级为八维：代码安全+Skill供应链+MCP权限+提示注入+数据外泄+特权升级+BIV完整性+MCP Server审计。 触发：合并PR前、Skill安装前、MCP Server部署前、功能实现后、重构后、bug修复后、方案提交前。
多维度质量审查，覆盖五轴（正确性/可读性/架构/安全/性能）+ Agent Skill安全审计（NVIDIA SkillSpector 16类漏洞模式 + Palo Alto BIV声明-行为完整性验证 + MCP Server安全审计）。…
As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:279Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)3. **依赖锁定**：检查是否有 unpinned deps（`*` 版本）或 `curl | bash`
detector -
low Dangerous commands
cmd-privilegeSKILL.md:84Privilege escalation / world-writable permissions (detector / deny-list definition; documentation table row)| 特权升级(3种) | sudo/root/cron 持久化 | grep `sudo`/`chmod 777`/`cron`/`systemctl` |
detectortable -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:85Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; documentation table row)| 供应链(6种) | 未锁定依赖、`curl\|bash`、混淆代码 | 检查 unpinned deps / Base64 / `eval()` |
detectortable
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 39/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (code-review-and-quality) differs from the folder (mimo-code-review-and-quality)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 115 steps
- 100Execution cost. Instruction body is 2704 tokens
- low 11 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
- +1No license
- +2Single-language instructions
- +3Description length 280: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 115 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.