Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
alibaba avatar

Security Check

  • 2 installs
  • 2.2k repo stars
  • Updated July 27, 2026
  • alibaba/loongcollector

security-check is a Claude skill that scans staged changes and commits for leaked API keys and tokens before commit or push and blocks the action if secrets are found.

About

This skill scans code for sensitive information such as API keys and access tokens before a commit or push. A developer uses it to run a pre-commit check on the staging area and a pre-push check across commits, detecting patterns like sk-, AIzaSy, and pk_ keys. If secrets are found it requires replacing them with placeholders or environment variables and refusing the commit or push, and it can clean git history.

  • Scans staged changes and commits for secrets before commit/push
  • Detects API keys and tokens like sk-, AIzaSy, and pk_ prefixes
  • Refuses the commit/push and can clean history when secrets are found

Security Check by the numbers

  • 2 all-time installs (skills.sh)
  • +1 installs in the week ending Jun 23, 2026 (Skillselion tracking)
  • Ranked #1,788 of 2,203 Security skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
At a glance

security-check capabilities & compatibility

Capabilities
security audit
Works with
github
Use cases
security audit
Pricing
Free
From the docs

What security-check says it does

Security scanning before commit/push. Checks for sensitive information like API keys and tokens.
SKILL.md
API Keys starting with `sk-` (OpenAI, Anthropic, Alibaba Cloud, etc.)
SKILL.md
npx skills add https://github.com/alibaba/loongcollector --skill security-check

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2
repo stars2.2k
Last updatedJuly 27, 2026
Repositoryalibaba/loongcollector

What it does

Scan staged changes and commits for leaked API keys and tokens before committing or pushing.

Who is it for?

Preventing accidental commits of API keys and access tokens by scanning staging and commit history

When should I use this skill?

Before committing or pushing code, to check for leaked secrets

What you get

A blocked commit/push when secrets are detected, with guidance to replace them and clean history

  • secret scan result
  • blocked commit/push on detection
  • cleaned git history

By the numbers

  • Detects 3 named key prefixes (sk-, AIzaSy, pk_)

Files

SKILL.mdMarkdownGitHub ↗

Security Check Rules

Before committing or pushing code, must check for sensitive information, especially API Keys and access tokens.

What to Check

API Keys and Access Tokens

  • API Keys starting with sk- (OpenAI, Anthropic, Alibaba Cloud, etc.)
  • Google API Keys starting with AIzaSy
  • Public keys starting with pk_
  • Other common API token formats

Before Commit

Run Check First

Run bash .claude/skills/security-check/scripts/security_check.sh commit to check the staging area for sensitive information. If it does NOT output staging area is clear, sensitive information was found.

If Sensitive Information Found

1. Immediately delete or replace: Replace real API Keys with placeholders 2. Use environment variables: Move sensitive info to environment variables 3. Add to .gitignore: Ensure files with sensitive info are not committed 4. Must refuse the commit/push action

Before Push

Run Check First

Run bash .claude/skills/security-check/scripts/security_check.sh push to check each commit for sensitive information. If it does NOT output all commits are clear, sensitive information was found. The commit hashes are written to task/sensitive_commits.txt.

If Sensitive Information Found

1. Immediately delete or replace: Replace real API Keys with placeholders 2. Use environment variables: Move sensitive info to environment variables 3. Add to .gitignore: Ensure files with sensitive info are not committed 4. Must use the script below to clean history

# Reset based on results in task/sensitive_commits.txt to avoid leaking commits
bash .claude/skills/security-check/scripts/security_reset.sh

5. Must refuse the commit/push action

Related skills

FAQ

What secret patterns does it detect?

API keys starting with sk-, Google keys starting with AIzaSy, public keys starting with pk_, and other common token formats.

What happens if a secret is found?

The skill requires replacing the secret with a placeholder or environment variable, adding it to .gitignore, and refusing the commit or push.

Securitysecretsappsec

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.