- Home
- Skills
- Legal & Compliance
- Credential Handling Safety Reviewer
Works with the AI Agents you already use
Credential Handling Safety Reviewer
Review scripts and docs for safer handling of passwords, tokens, keys, and sensitive values.
$24.99
Credential Handling Safety Reviewer
Example session with this skill installed
Please review this redacted bash script for any sensitive value handling issues and suggest safer patterns for the API token and tenant ID.
- Read your context and instructions
- Compiled the credential handling safety
**Hygiene Verdict:** NEEDS CHANGES - Risk: Token passed as environmental variable in script; visible in 'ps' output. - Fix: Replace with 'security find-generic-password' lookup. - Redaction: Line 14 contains a hardcoded placeholder that resembles a production tenant ID. Use UUID variable.
Connects securely to your tools. The creator never sees your data.
About this skill
Defensive review for sensitive-value handling
Credential Handling Safety Reviewer reviews scripts, runbooks, and configuration notes for safer handling of passwords, tokens, keys, and other sensitive values.
What it checks
- Sensitive values placed in scripts, tickets, docs, or config snippets.
- Prompt and variable patterns that may appear in logs, shell history, process listings, or temporary files.
- Keychain and secret-store assumptions from redacted examples.
- Token lifecycle notes covering scope, owner, expiration, rotation, and revocation planning.
- Support log cleanup guidance that preserves troubleshooting value.
Boundaries
Use redacted or synthetic examples. This skill does not collect, validate, store, transmit, or request live passwords, API tokens, recovery keys, private tenant values, or private customer data.
Output
You get a hygiene verdict, redaction notes, safer handling patterns, token lifecycle checklist, and peer-review remediation notes.
- Cannot detect if a placeholder is actually a live secret. - No real-time integration with secret managers. - Limited to static analysis of scripts and text.
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 5 months ago
Permissions
No special permissions declared or detected