Dangerous Command Linter
Flag the destructive operations in a shell command or script before anyone runs it.
What it does
- Recursive force deletes.
- Force pushes.
- History rewrites.
- Database drops.
- Truncates.
- Disk-wipe commands.
- Permission blowouts.
- Remote content piped into a shell.
Catches recursive force deletes, force pushes and history rewrites, database drops and truncates, disk-wipe commands (mkfs, dd to a device), permission blowouts (chmod 777), remote content piped into a shell, broad wildcard deletes, and prod-targeting or disabled-safety flags. Each finding comes with a severity and a safer alternative.
How to run
Get it on Agensi and run it with any agent that reads SKILL.md, such as Claude Code, Codex, or Cursor. The listing includes setup steps and exactly what it reads.
Good to know
Works with any assistant that reads the open SKILL.md standard. Not locked to a single tool or vendor.
Questions
What does Dangerous Command Linter do?
Flag the destructive operations in a shell command or script before anyone runs it.
What does it need to run?
It works with anything that reads SKILL.md, so it is not tied to one tool or vendor.
Add Dangerous Command Linter to your toolkit.
Current price and purchase option are shown on Agensi. Instant download. Works with any agent that reads SKILL.md.
Get Dangerous Command Linter on Agensi