Works with the AI Agents you already use
Secret Leak Scanner
Scans your codebase or staged git changes for accidentally committed API keys, AWS credentials, private keys and tokens before you push.
$5
Secret Leak Scanner
Example session with this skill installed
Check my staged changes for any secrets before I commit.
- Read your context and instructions
- Compiled the secret leak scanner
[HIGH] config.py:1 AWS Access Key ID -> AKIA************MNOP
[HIGH] config.py:2 AWS Secret Access Key -> aws_**********************************************************KEY
[MEDIUM] config.py:2 Env-style Secret Assignment -> aws_**********************************************************KEY
[HIGH] config.py:3 Stripe Secret Key -> sk_l*****************************STUV
[HIGH] config.py:4 DB Connection String w/ password -> post**********************************************prod
Scan complete. 5 potential finding(s).
Review each finding — HIGH severity items should be treated as real leaks until proven otherwise.
Summary: Found 4 high-confidence leaks (AWS key pair, Stripe live key, DB connection string with embedded password) and 1 medium-confidence finding. Recommend rotating the AWS and Stripe keys immediately since they were staged for commit, moving all four values to environment variables, and adding config.py to .gitignore before committing again.
Connects securely to your tools. The creator never sees your data.
About this skill
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
Regex + entropy-based detection can miss cleverly obfuscated or split secrets, and may false-positive on random-looking test data, hashes, or UUIDs. Not a replacement for a dedicated enterprise secret-scanning service (e.g. GitHub secret scanning, TruffleHog) for large-scale production monitoring — this is a fast local first line of defense. History scanning (--history mode) can be slow on repos with a large number of commits.
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 buying a skill.
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 3 months ago
- Software
Python
Permissions
File Scopes
Reads source files and git metadata (diff/log/show) to detect secrets. No files are modified. No network requests are made — all pattern matching happens locally.