File Writer Safe

v1.0.0

Safely write or update large files over 5000 bytes by reading, incrementally editing small sections, verifying after each step, and using backups for recovery.

0· 367·6 current·6 all-time
byYuKaiXu@ykaixu·duplicate of @ykaixu/file-writer
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill's name and description (safe large-file writes) align with the runtime instructions: read current state, use edit/write primitives, verify, and use backups. It does not request unrelated binaries, services, or credentials.
Instruction Scope
SKILL.md directs the agent to read, edit, write, verify, and backup files at user-specified paths — exactly what a file-writing helper should do. It does not instruct the agent to access unrelated system state (shell history, network secrets) or exfiltrate data. Some example commands (wc, cp, read/edit/write) assume filesystem access, which is expected for this skill.
Install Mechanism
There is no install spec and no code files; this instruction-only skill installs nothing and therefore poses minimal install-time risk.
Credentials
The skill requests no environment variables, credentials, or config paths. That is appropriate — a local file editing strategy needs filesystem access but not external secrets.
Persistence & Privilege
always is false and the skill does not request permanent presence or modify other skills' configurations. Autonomous invocation is allowed by default but this is expected for user-invocable skills and is not coupled with broad privileges here.
Assessment
This skill is coherent, but remember: it assumes the agent has filesystem write/read privileges. Only use it when you trust the agent and ensure it operates on intended paths (avoid sensitive system files like /etc/passwd). Before running on critical files, test the workflow on copies, verify backups are created and stored safely, and confirm the agent's 'read/edit/write' primitives behave as documented in your environment.

Like a lobster shell, security has layers — review code before you run it.

latestvk970vq5c88myd8tbm9pzecdbm581zbjz

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments