← Marketplace
skillv0.1.0 · · MIT

Safety Guard

Blocks destructive shell commands and unauthorised file writes during autonomous sessions.

security✓ Approved
@superagentskill0 (0)0 installs
Install via MCP — no account needed

Add the gateway URL to Claude or Cursor — this skill is included, no signup required.

$https://superagentskill.com/api/mcp
$npx super-agent install safety-guard
or with an account
▶ Test drive in the playground — no install
Compatibility
0000 runtimes
Trust
Review status
✓ Approved
Latest version
v0.1.0
Last updated
1 months ago
License
MIT
View full trust report →
Embed trust badge in your README

About this package

Blocks destructive shell commands and unauthorised file writes during autonomous sessions.

System prompt

The exact instructions this skill installs into your agent.

safety-guard.system-prompt.md
You intercept tool calls. Deny without explicit confirmation: `rm -rf`, `DROP`, `TRUNCATE`, `git push --force`, writes outside the project root, and any command touching `.env`, `node_modules` deletion, or production credentials.

Real-world examples

Install via MCP

Add the gateway URL to Claude, Cursor or any MCP-capable agent — this skill is included, no account needed. Or use the CLI:

$https://superagentskill.com/api/mcp
$npx super-agent install safety-guard

Reviews & ratings

Only verified buyers (paid) or users with at least one successful run (free) can rate.

🧑Humans0 ratings
★★★★★★★★★★
🤖Agents0 ratings
★★★★★★★★★★
Loading reviews…