Agent skill · Audited from source

flash-jlink

skill · leokemp223/embed-ai-toolLicence not declaredAudited 29 Oct 2026 · source f2eee4d05246

★ 1,045pushed 70 days ago
✓SAFEGrade B · 89/100 · 29 Oct 2026 · f2eee4d
1,045repo stars · whole leokemp223/embed-ai-tool

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: 当需要使用 SEGGER J-Link 探针烧录固件,或启动 RTT 日志捕获时使用。

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “flash-jlink (leokemp223/embed-ai-tool)”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/leokemp223/flash-jlink

Trust audit

Audit 0.4.1 · source read 29 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 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

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS1
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass, no license.

Findings (1)

LOWInventory / provenanceinv.no_license
F-13 Inventory / provenanceCWE-1104Layer L0
Why
no LICENSE file and no repo licence
Fix
add a licence

Audit 0.4.1 · source sha f2eee4d05246 · 29 Oct 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/flash-jlinkThe 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 70 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: 当需要使用 SEGGER J-Link 探针烧录固件,或启动 RTT 日志捕获时使用。

---
name: flash-jlink
description: 当需要使用 SEGGER J-Link 探针烧录固件,或启动 RTT 日志捕获时使用。
---

# J-Link 烧录

## 适用场景

- 工作区已有可用固件产物,且目标板连接了 SEGGER J-Link 探针。
- 需要使用 J-Link Commander 进行烧录和校验,而非 OpenOCD。
- 需要利用 J-Link RTT(Real-Time Transfer)进行高速日志捕获。
- 需要扫描工作区中的 `.jlink` 配置文件或 `.vscode/launch.json` 中的 J-Link 设置。

## 必要输入

- 固件产物路径,或包含 `artifact_path` 的 `Project Profile`。
- `--device` 参数指定目标芯片型号(如 `STM32F407VG`),J-Link Commander 要求必须指定。
- 可选的接口类型(SWD 或 JTAG,默认 SWD)和烧录速度。
- 若产物为 BIN,还需要 `--base-address` 烧录基地址。

## 自动探测

- 脚本启动即自动复用工程根目录 `.em_skill.json` 中上次成功的 profile 作为默认参数(显式参数优先,无需先手动传 `--resume`);`--resume` 仅用于断言缓存必须存在,无缓存则非零退出。无缓存或用户明确要求重新探测时,脚本自动回退到正常扫描。
- 按 `ELF > HEX > BIN` 选择固件产物。
- 脚本自动查找 JLinkExe,按配置文件、PATH、常见安装路径的顺序搜索。
- `--scan-configs` 扫描工作区 `.jlink` 文件和 `.vscode/launch.json` 中的 J-Link 配置。
- 不会猜测设备名;当 `--device` 缺失时阻塞并返回 `ambiguous-context`。

## 执行步骤

1. 先阅读 [references/usage.md](references/usage.md),确认本次是环境探测、配置扫描,还是执行烧录。
2. 若不确定 J-Link 环境状态,先运行自带脚本 [scripts/jlink_flasher.py](scripts/jlink_flasher.py) 的 `--detect` 模式确认。
3. 若不确定设备型号或接口配置,使用 `--scan-configs` 扫描工作区线索。
4. 使用 `--artifact` + `--device` 执行烧录,可选 `--interface` 和 `--speed`。
5. 对 BIN 文件,必须同时提供 `--base-address`。
6. 需要 RTT 日志时,使用 `--rtt` 启动 RTT 捕获。
7. 读取脚本输出的烧录结果报告,重点关注校验状态和失败分类。

## 失败分流

- 当 `JLinkExe` 不可用时,返回 `environment-missing`。
- 当无法安全解析到产物,或 `BIN` 缺少烧录基地址时,返回 `artifact-missing`。
- 当 J-Link 无法发现探针或目标时,返回 `connection-failure`。
- 当配置文件无效或设备名不被 J-Link 识别时,返回 `project-config-error`。
- 当烧录开始但校验或复位失败时,返回 `target-response-abnormal`。
- 当 `--device` 缺失且无法从工作区推断时,返回 `ambiguous-context`。

## 平台说明

- JLinkExe 在 Linux/macOS 下为 `JLinkExe`,Windows 下为 `JLink.exe`。
- SEGGER 默认安装路径:Linux `/opt/SEGGER/JLink/`,Windows `C:\Program Files\SEGGER\JLink\`。
- 自带脚本使用 Python 标准库和 subprocess 调用 JLinkExe,跨平台兼容。
- RTT 功能为 J-Link 独有,不占用 UART,适合无串口场景。

## 输出约定

- 输出 JLinkExe 命令、设备名、接口类型、产物路径和校验结果。
- 在 `Project Profile` 中保留或更新 `artifact_path`、`artifact_kind`、`jlink_device`、`jlink_interface`。
- 烧录成功后推荐 `serial-monitor` 或 `debug-jlink`。

## 交接关系

- 当下一步要看运行日志时,将成功烧录结果交给 `serial-monitor`。
- 当用户需要 GDB 调试时,将结果交给 `debug-jlink`。
- 当需要 RTT 日志替代串口时,可直接使用本 skill 的 `--rtt` 模式。

Excerpt, first 2,129 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

Download folder ↗
git clone https://github.com/leokemp223/embed-ai-tool
git -C embed-ai-tool checkout f2eee4d05246

The author documents no install command, so this uses the repository directly. 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

  1. ✓SAFE B 89 / 100

    first audit · source f2eee4d05246

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/leokemp223/flash-jlink/badge.svg)](https://modelsatlas.com/skills/leokemp223/flash-jlink/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/leokemp223/flash-jlink/badge.svg)](https://modelsatlas.com/skills/leokemp223/flash-jlink/)

Questions about flash-jlink

What does the flash-jlink skill do?
面向 AI 编程助手的嵌入式开发技能集,为大模型提供 MCU 固件开发全流程能力。涵盖多工具链构建(Keil / IAR / CMake / PlatformIO)、烧录、GDB 调试、串口监视、Modbus / CAN / VISA 协议调试、外设驱动适配及流水线编排,支持 Linux、macOS、Windows 三平台。
Is flash-jlink safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can flash-jlink access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (f2eee4d05246), read on 2026-10-29. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

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.