Marketplace for trusted AI agent skills

Block secret leaks before commit or push with ggshield

Skill Detail

Block secret leaks before commit or push with ggshield

Scan staged changes, commits, or repositories for secrets before they leave the workstation or CI job, instead of relying on a later platform-side catch.

Security & VerificationMulti-Framework
Security & Verification Multi-Framework Published
⭐ 1.9k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill block-secret-leaks-before-commit-or-push-with-ggshield Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
View source
At a glance
Tools required
Python environment or packaged ggshield install, Git, optional GitGuardian API key for full detector coverage
Install & setup
Install ggshield with pipx, pip, or Homebrew, optionally run `ggshield auth login` or set a GitGuardian API key, then invoke checks such as `ggshield secret scan pre-commit`, `ggshield secret scan pre-push`, or `ggshield secret scan repo`.
Author
GitGuardian
Publisher
Organization
Last updated
Apr 20, 2026
Quick brief

Use ggshield when an agent needs a pre-commit, pre-push, or CI guardrail that checks code changes for leaked credentials before they are shared. The agent can scan staged diffs, recent commits, or whole repositories and return concrete secret findings early enough to stop the handoff. The scope boundary is specific: this skill is about running GitGuardian’s local scanning workflow at the change boundary, not about publishing a generic secret-management or SaaS product card.