Agent skill · Audited from source
serial-monitor
skill · leokemp223/embed-ai-toolLicence not declaredAudited 13 Nov 2026 · source f2eee4d05246
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit f2eee4d05246 and found no filesystem, network or shell access and no hard-coded secrets. What it does: 当需要识别正确串口、调用自带脚本抓取日志,并分析嵌入式固件运行状态时使用。
Cite
Cite this page
ModelsAtlas. “serial-monitor (leokemp223/embed-ai-tool)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/leokemp223/serial-monitor
Trust audit
Audit 0.4.1 · source read 13 Nov 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass, no license.
Findings (1)
LOWInventory / provenanceinv.no_license
- Why
- no LICENSE file and no repo licence
- Fix
- add a licence
Audit 0.4.1 · source sha f2eee4d05246 · 13 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherleokemp223 GitHub userOwner of the repository this skill is read from
- Source folderleokemp223/embed-ai-tool/skills/serial-monitorThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdictf2eee4d05246A new audit runs when the source changes
- Repository statusNot archivedLast push 85 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: 当需要识别正确串口、调用自带脚本抓取日志,并分析嵌入式固件运行状态时使用。
--- name: serial-monitor description: 当需要识别正确串口、调用自带脚本抓取日志,并分析嵌入式固件运行状态时使用。 --- # 串口监视 ## 适用场景 - 用户需要查看目标板的启动日志、断言输出或交互式 UART 输出。 - 烧录或复位刚完成,下一步需要观察运行期行为。 - 需要避免错过早期启动日志,或希望在监听后立即复位目标板。 - 工作区或 profile 中已经有明确的 UART 端口或波特率。 ## 必要输入 - 一个串口,或一份足以完成串口探测的 `Project Profile`。 - 可选的波特率、监视模式、关键字符串、日志保存路径。 - 若要自动复位,还需要 OpenOCD 配置,来自显式输入或已有工程画像。 ## 自动探测 - 串口优先级为:显式用户输入、`Project Profile`、脚本自动检测结果,否则阻塞。 - 波特率优先级为:显式用户输入、`Project Profile`、工作区文档或代码常量,最后回落到 `115200`。 - 自动检测时,优先选择 CH340、CP210x、CMSIS-DAP、ST-Link 等常见串口或调试器虚拟串口。 - 若存在多个同样合理的串口候选,先列出候选,再按需要阻塞而不是静默猜测。 ## 执行步骤 1. 先阅读 [references/usage.md](references/usage.md),确认本次是列表、抓取、等待字符串、持续监视,还是“先监听后复位”。 2. 运行自带脚本 [scripts/serial_monitor.py](scripts/serial_monitor.py)。列出串口时使用 `--list`,自动选择端口时使用 `--auto`。 3. 普通抓取使用 `--duration`,等待特定输出使用 `--wait`,持续监视使用 `--monitor --timestamp`。 4. 若担心错过早期启动日志,使用 `--wait-reset`;只有在 OpenOCD 配置已经明确时,才启用 `--auto-reset`。 5. 读取脚本输出的分析结果,而不是只转述原始串口文本;重点关注错误、警告、启动标记和关键外设关键词。 6. 将选中的串口、波特率、命令和日志结论写回 `Project Profile`,并在需要时交给下游 skill。 ## 失败分流 - 当缺少 `pyserial` 或 `openocd` 等依赖时,返回 `environment-missing`。 - 当选中的串口无法打开或在监视过程中消失时,返回 `connection-failure`。 - 当宿主机没有权限访问串口设备时,返回 `permission-problem`。 - 当存在多个合理串口候选,或工作区中隐含互相冲突的波特率时,返回 `ambiguous-context`。 - 当串口可访问,但日志明显表现为启动失败、重复复位、断言或 Fault 时,返回 `target-response-abnormal`。 ## 平台说明 - Linux、macOS、Windows 的串口命名规则复用 [platform-compatibility.md](/home/leo/work/open-git/em_skill/shared/platform-compatibility.md)。 - 自带脚本使用 `pyserial`,因此串口抓取路径本身是跨平台的。 - Windows 输出中要保留准确的 `COM` 端口名,以及 shell 需要的命令行引号形式。 ## 输出约定 - 输出选中的串口、波特率、实际执行命令,以及对日志分析结果的简洁总结。 - 当串口和波特率被明确后,用 `serial_port` 和 `baud_rate` 更新 `Project Profile`。 - 若使用了 `--auto-reset`,同时记录 OpenOCD 配置来源和复位命令。 - 当日志表明程序崩溃、卡死或启动异常时,推荐 `debug-gdb-openocd`。 ## 交接关系 - 当日志显示需要断点、寄存器或回溯时,将结果交给 `debug-gdb-openocd`。
Excerpt, first 1,784 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit f2eee4d
pip install pyserial
git clone https://github.com/leokemp223/embed-ai-tool git -C embed-ai-tool checkout f2eee4d05246
Commands as the repository documents them: shown, never run by us. Our verdict covers commit f2eee4d05246 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
f2eee4d05246
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/leokemp223/serial-monitor/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
All coding & review skills →leokemp223/embed-ai-tool
当需要对嵌入式 C/C++ 代码运行 cppcheck、clang-tidy 或 GCC analyzer 静态分析,或进行 MISRA-C 合规检查时使用。
leokemp223/embed-ai-tool
当需要解析 .map 文件或 ELF 获取固件内存使用报告、符号大小排名或版本对比时使用。
leokemp223/embed-ai-tool
当需要调试 Modbus RTU(串口)或 Modbus TCP(网络)设备通信时使用,支持寄存器读写、从站扫描和持续监控。
leokemp223/embed-ai-tool
嵌入式开发技能集的总控入口。负责两类任务:(1) 用户请求安装本仓库 skill 时,引导选择全部或按需安装;(2) 用户发出模糊指令(如"烧录"、"编译"、"调试")且无法自动判断应使用哪个具体 skill 时,列出同分类下的候选 skill 供用户选择。
leokemp223/embed-ai-tool
当需要进行 FreeRTOS/RT-Thread/Zephyr 的线程感知调试,查看任务列表、栈水位或死锁检测时使用。
leokemp223/embed-ai-tool
当需要使用已探测或显式指定的产物与探针配置,调用自带脚本通过 OpenOCD 烧录嵌入式固件时使用。
Add this badge to your README
[](https://modelsatlas.com/skills/leokemp223/serial-monitor/)
<a href="https://modelsatlas.com/skills/leokemp223/serial-monitor/"><img src="https://modelsatlas.com/skills/leokemp223/serial-monitor/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about serial-monitor
What does the serial-monitor skill do?
Is serial-monitor safe to install?
What can serial-monitor access on my machine?
How current is this page?
Sources
- github.com/leokemp223/embed-ai-tool/tree/master/skills/serial-mo — the audited source at commit f2eee4d05246 and every finding aboveObserved · 13 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the serial-monitor skill do?
- Is serial-monitor safe to install?
- What can serial-monitor access on my machine?