Coze
Official siteLow-code agent workflow platform for fast automation delivery.
OpenBack to template library
Automated Vulnerability Scan and Alert Workflow with GitHub
DevelopmentCozeUpdated 2026-03-08
Automatically run vulnerability scans on a GitHub repository, filter high‑severity findings, and notify the development team via Slack or email, ready for CI/CD integration.
System Prompt
Run vulnerability scan on {repo_url} at branch {branch} using {scan_type} mode. Filter results with severity >= {severity_threshold}. If any, create GitHub issue and send notification to {notification_channel}.Variable Dictionary (fill in your AI tool)
This section only explains placeholders. It is not an input form on this website. Copy the prompt, then replace variables in Coze / Dify / ChatGPT.
{repo_url}HTTPS URL of the target repository, e.g., https://github.com/owner/repo
Filling hint: replace this with your real business context.
{branch}Branch to scan, e.g., main or develop
Filling hint: replace this with your real business context.
{scan_type}Scan mode, options: full (complete scan) or incremental (delta scan)
Filling hint: replace this with your real business context.
{severity_threshold}Minimum severity to report, e.g., high, medium, or low
Filling hint: replace this with your real business context.
{notification_channel}Alert channel, options: slack, email, or webhook
Filling hint: replace this with your real business context.
Quick Variable Filler (Optional)
Fill variables below to generate a ready-to-run prompt in your browser.
{repo_url}HTTPS URL of the target repository, e.g., https://github.com/owner/repo
{branch}Branch to scan, e.g., main or develop
{scan_type}Scan mode, options: full (complete scan) or incremental (delta scan)
{severity_threshold}Minimum severity to report, e.g., high, medium, or low
{notification_channel}Alert channel, options: slack, email, or webhook
Generated Prompt Preview
Missing: 5
Run vulnerability scan on {repo_url} at branch {branch} using {scan_type} mode. Filter results with severity >= {severity_threshold}. If any, create GitHub issue and send notification to {notification_channel}.How to Use This Template
Best for
Teams that need faster development output with more stable prompt quality.
Problem it solves
Reduces blank-page time, missing constraints, and inconsistent output structure from ad-hoc prompting.
Steps
- Copy the template prompt.
- Paste it into your AI tool (Coze / Dify / ChatGPT).
- Replace placeholder variables using the dictionary above.
- Run and refine constraints based on output quality.
Not ideal when
You need live web retrieval, database writes, or multi-step tool orchestration. Use full workflow automation for that.
Success Case
Input:
repo_url: https://github.com/example/repo
branch: main
scan_type: full
severity_threshold: high
notification_channel: slack
Output:
Scan completed, 3 high‑severity vulnerabilities found.
Created 3 GitHub Issues.
Sent notification to Slack.
Boundary Case
Input:
repo_url:
branch: main
scan_type: full
severity_threshold: high
notification_channel: slack
Fix:
Provide a valid GitHub repository HTTPS URL.
What to Try Next
Keep exploring with similar templates and matching tools.
Continue Where You Left Off
No recent items yet.
Workflow Steps
1️⃣ Trigger the GitHub Security Lab Taskflow Agent with {repo_url}, {branch}, and {scan_type}.
2️⃣ Wait for scan completion and retrieve the results list.
3️⃣ Filter findings by {severity_threshold} to isolate high‑severity issues.
4️⃣ For each high‑severity vulnerability, create a GitHub Issue with detailed info.
5️⃣ Send the scan report to the team via {notification_channel}.
Constraints
- If no high‑severity vulnerabilities are found, the system should return "No high severity vulnerabilities found."
- Large repositories may timeout; consider using incremental scan mode for faster results.
Explore More in This Category
Development
Similar Templates
Recommended Stack
Tools that work well with this template.
OpenAI
Official siteGeneral LLM platform for generation, analysis, and development use cases.
Open