Works with the AI Agents you already use
Security Hygiene Checklist
Automated scanner for security misconfigurations, credential exposure risks, and unsafe environment settings.
Free
Security Hygiene Checklist
Example session with this skill installed
Run a security hygiene check on this repo before I push it to GitHub.
- Read your context and instructions
- Compiled the security hygiene checklist
Security Hygiene Report
- CRITICAL:
.envis currently tracked by git. Rungit rm --cached .env. - WARNING:
DEBUG = Truefound inconfig/settings.py. - RISK:
verify=Falsefound inapi_client.py. - HYGIENE: Missing
package-lock.json. Supply chain is unpinned.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Leaking secrets is a disaster, but the structural misconfigurations that lead to those leaks often go unnoticed during development. Manual audits are tedious, and simple secret scanners miss the underlying setup issues like missing gitignore rules or disabled TLS verification.
What it does
- Identifies sensitive files like .env or .pem that are already committed to git history.
- Scans for dangerous configuration patterns including wildcard CORS and disabled SSL/TLS verification.
- Flags active debug modes in application config files that could expose stack traces.
- Validates .gitignore coverage against common credential and key patterns.
- Checks for missing dependency lockfiles to ensure supply chain consistency.
Frameworks & tools
Works with any codebase. Specifically detects patterns for Python (requests, Flask/Django), Node.js, and standard web configuration formats.
Why this beats prompting it yourself
Writing a prompt to find "security issues" often results in hallucinations or missed edge cases like git-tracked files. This skill uses a codified heuristic approach to check specific, high-risk structural patterns that a generic LLM pass would likely overlook.
Use cases
- Pre-launch audits to ensure production settings are hardened.
- Reviewing a private repo before making it public or open-source.
- Baseline security checks when onboarding a legacy codebase.
- Quick hygiene passes before major releases.
Known limitations
This is a heuristic configuration scanner, not a full static analysis (SAST) or dependency vulnerability (CVE) tool. It cannot confirm if a flagged file is actually used in production.
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.
Heuristic-based, not a full SAST/CVE scan. Cannot verify if flagged config is actually deployed to production. Requires Python and Git on PATH.
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
This skill has been used 3 times.
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
- Software
Python