secret scanner
Scan repositories for leaked secrets, API keys, and tokens
$9
Works with the AI Agents you already use
secret scanner
Example session with this skill installed
Scan the /project directory for any leaked secrets or API keys.
- Read your context and instructions
- Compiled the secret scanner
Secret Scan Report: /project
Summary: 4 findings (1 Critical, 2 High, 1 Medium)
| File | Line | Type | Severity | Snippet |
|---|---|---|---|---|
| config.py | 12 | AWS Access Key | 🔴 Critical | AKIA****...****XY2 |
| .env | 3 | GitHub Token | 🟠 High | ghp_****...****aBc |
| api.js | 47 | JWT Secret | 🟠 High | secr****...****key |
| docker-compose.yml | 8 | DB Password | 🟡 Medium | pass****...****123 |
Recommendations
- Rotate all exposed credentials immediately
- Remove secrets from git history (git filter-repo)
- Add secrets to .gitignore or use environment variables
- Enable secret scanning in CI/CD pipeline
⚠️ Report generated with explicit authorization.
Connects securely to your tools. The creator never sees your data.
About this skill
Secret Scanner Skill
Detect accidentally committed secrets, API keys, tokens, and credentials in code repositories. Uses pattern matching and entropy analysis — no external dependencies.
What it does
- Scans files for common secret patterns (AWS keys, GitHub tokens, JWT, private keys)
- Uses entropy analysis to detect high-randomness strings
- Classifies findings by severity (Critical, High, Medium, Low)
- Generates a report with file locations and remediation steps
Perfect for
- Security engineers auditing repositories
- Developers preventing credential leaks
- DevSecOps teams integrating security into CI/CD
Includes
- SKILL.md with detection methodology
- Pattern library for common secret types
- Structured report template
Works with
Any MCP-compatible agent (Claude Code, Cursor, OpenClaw, Codex CLI, Gemini CLI).
⚠️ Disclaimer
Only scan repositories you own or have explicit permission to scan. Never exfiltrate discovered secrets.
Does not verify if secrets are active or revoked. Limited to text-based scanning within the provided repository context.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
No special permissions declared or detected