letter-shell-integration — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited letter-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 letter-shell as an embedded debug console safely. Prove the transport, shell task or polling loop, command registration, and authorization policy before exposing commands that modify flash, reset devices, or change production state.
Use this skill when:
Do not use this skill when the serial port itself is not trustworthy. Use embedded-serial-log-debug first.
Ask for:
Confirm raw RX/TX works before debugging shell parsing.
Bind it to explicit read/write functions and initialize it once.
Use a polling loop for simple bare-metal demos or a dedicated task/event-driven model for RTOS projects.
Start with version, help, or status before adding state-changing commands.
If commands are exported through sections/macros, ensure the linker script and optimization settings keep them.
Commands that erase flash, format filesystems, reset devices, change boot config, or modify calibration require explicit user/product approval.
Before claiming letter-shell works:
help or an equivalent harmless command works.User:
想接 letter-shell,通过串口输入命令查看系统状态。Agent:
status command and confirms help can list it.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.