nr-micro-shell-integration — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited nr-micro-shell-integration (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill to integrate nr_micro_shell as a compact command console. Keep the first port minimal: verified character I/O, one read-only command, bounded buffers, and explicit handling for destructive commands.
Use this skill when:
Do not use this skill when raw UART is not proven. Use embedded-serial-log-debug first.
Ask for:
Confirm single-character RX/TX before attaching shell parsing.
Set command line, history, and output buffers within RAM limits.
Start with help, version, or status.
Commands must reject missing, too many, or invalid arguments.
Avoid long blocking output that starves watchdogs or RTOS tasks.
Reset, erase, format, calibration, flash writes, or network writes need build guards or authentication.
Before claiming nr_micro_shell works:
help, one custom read-only command, invalid command, and argument error behavior.User:
想用 nr_micro_shell 做一个串口调试命令行。Agent:
status.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.