More screenshots
Works with the AI tools you already use
⚠️ Dangerous Command Linter
It identifies destructive, irreversible, or high-risk operations that could lead to data loss or system instability.
$12
⚠️ Dangerous Command Linter
Example session with this skill installed
Is it safe to run this? curl -sSL https://install.example.com | sudo bash
- Read your context and instructions
- Compiled the dangerous command linter
Findings:
[High] Pipe-to-Shell: Remote content is piped directly to sudo bash.
- Evidence:
curl ... | sudo bash - Risk: Unverified remote execution.
- Alternative: Download script, inspect manually, then run:
curl -O [URL] && less [file]
Scope:
1 command string.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
Safety First for Shell Operations
The Dangerous Command Linter is a specialized security tool designed for developers and DevOps engineers who want an extra layer of protection before executing shell commands or scripts. It identifies destructive, irreversible, or high-risk operations that could lead to data loss or system instability.
What it does
This skill performs a heuristic analysis on shell scripts (.sh, .bash, .zsh, .ps1) and raw CLI strings. It scans for patterns including recursive deletions, force pushes, database drops, permission overrides (chmod 777), and the "curl | sh" anti-pattern. Unlike a standard LLM prompt, it utilizes a dedicated Python scanner and a curated JSON database of dangerous patterns to ensure consistent, rule-based detection.
Supported Tools & Frameworks
- Bash, Zsh, and PowerShell scripts
- Git, Docker, and Cloud CLI commands
- Standard Linux/Unix system utilities (rm, chmod, chown)
- Database CLI tools
Why use this skill?
While an AI can "guess" if a command is bad, this skill follows a structured audit workflow. It provides a formal report categorizing findings by severity, identifies the exact line of concern, and suggests safe alternatives or remediation snippets. It acts as a pre-execution linting layer for your terminal workflow, reducing the risk of "fat-finger" errors in production environments.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 3 months ago
- Passed all security checks, Safe to install