Works with the AI Agents you already use
secureflow
Agent-independent secure coding workflow featuring STRIDE threat modeling, OWASP ASVS mapping, evidence-based auditing, and deterministic security verification for C# and ASP.NET Core.
$2.99
secureflow
Example session with this skill installed
Run a security review on the new OrdersController.cs. Map requirements to ASVS and run the premium gate to verify the JWT and SQL injection controls.
- Read your context and instructions
- Compiled the secureflow
I have completed the security review for OrdersController.cs. I identified two high-risk assets (customer PII and order history) and verified controls against ASVS 5.0 requirements.
Security Audit Report: OrdersController.cs
| Control ID | Requirement | Status | Evidence |
|---|---|---|---|
| REQ-AUTHZ-001 | Only order owner/admin may read orders | PASS | OrdersController.cs:42 - [Authorize(Policy = "OwnerOrAdmin")] |
| REQ-INJ-001 | Parameterized SQL queries for lookups | PASS | OrdersController.cs:88 - db.QueryAsync<Order>(sql, new { id }) |
| SF-AUTH-006 | Require signed JWT tokens | FAIL | Program.cs:22 - ValidateIssuerSigningKey = false |
| SF-SEC-006 | No literal credentials in config | UNVERIFIED | Found appsettings.Development.json but could not verify production secrets. |
Gate Execution Summary
$ python scripts/secureflow-gate.py scan --profile premium-csharp-aspnetcore
[!] FAIL: SF-AUTH-006 detected in Program.cs (Line 22)
[?] UNVERIFIED: SF-SEC-006 (1 finding in environment files)
[+] PASS: SF-INJ-001 (Verified Dapper parameterization)
Scan failed with Exit Code 1.
Next steps
- Fix the JWT validation by setting
ValidateIssuerSigningKey = trueinProgram.cs. - Move the hardcoded development API key to a secure secret store to resolve the
UNVERIFIEDfinding. - Rerun the
secureflow-gate.py verify-reportcommand to confirm the fixes.
Connects securely to your tools. The creator never sees your data.
About this skill
SecureFlow Premium
Security should not be an afterthought in AI-assisted software development.
AI coding agents can produce code that appears secure without providing sufficient evidence to support their claims. SecureFlow Premium addresses this problem with a structured, prevention-first security workflow that combines threat modeling, security requirements, static analysis, and evidence-based verification.
What it does
- STRIDE threat modeling: Guides the identification of assets, entry points, trust boundaries, and potential threats, with mandatory human validation steps.
- Deterministic security gate: Uses a specialized Python-based verification tool to inspect repositories for security issues, including hardcoded secrets and insecure JWT configurations.
- ASVS and CWE mapping: Connects security requirements and findings to relevant OWASP Application Security Verification Standard (ASVS) 5.0 and Common Weakness Enumeration (CWE) references.
- Evidence-based auditing: Encourages verifiable security claims supported by file paths, line numbers, and evidence hashes.
- C# and ASP.NET Core analysis: Provides specialized static analysis for authentication, JWT validation, Dapper, SQL injection patterns, process execution, and credential handling.
How it works
- Scope and Map: Identify relevant assets, entry points, data stores, and trust boundaries before implementation.
- Model Threats: Apply STRIDE to identify threats and establish security requirements and testable controls.
- Verify with the Gate: Run the SecureFlow security gate to generate machine-readable reports and identify PASS, FAIL, and UNVERIFIED outcomes.
- Audit Claims: Compare security claims against repository evidence to reduce unsupported conclusions and improve auditability.
Frameworks and compatibility
SecureFlow Premium is designed for AI-assisted development and follows the open SKILL.md standard.
Compatible with OpenCode, Claude Code, Cursor, and GitHub Copilot.
The security gate requires Python 3.9 or later.
Deep static analysis is currently specialized for C# and ASP.NET Core projects.
Why SecureFlow Premium?
Generic instructions alone do not provide a reliable way to verify whether security requirements have actually been implemented.
SecureFlow Premium combines structured security guidance with deterministic verification tools, helping development agents move beyond assumptions and produce more traceable, evidence-based security assessments.
Use cases
- Reviewing API endpoints for object-level authorization risks, including BOLA and IDOR.
- Checking JWT signing, issuer, audience, and lifetime validation configurations.
- Producing evidence-based security reports for development and release reviews.
- Identifying SQL injection risks in Dapper and ADO.NET implementations.
- Reviewing credential exposure and insecure process execution patterns.
- Incorporating security requirements into AI-assisted software development workflows.
Known limitations
- Analysis is static and does not execute application-level DAST testing.
- Deep security analysis is currently limited to C# and ASP.NET Core.
- It does not replace SCA, historical secret scanning, professional penetration testing, or comprehensive security assessments.
- Static analysis can produce false positives and false negatives.
- Findings marked UNVERIFIED require interpretation and may not cause a non-zero exit code unless
--fail-on unverifiedis enabled. - Evidence hashes help identify changes but do not constitute a digital signature or guarantee report authenticity.
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.
Static analysis only; no DAST or dependency scanning. Deep rule support is limited to C# and ASP.NET Core. Requires Python 3.9+ for the gate script.
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 today
- Software
Pythonterminalshell