- Home
- Skills
- APIs & Backend
- Auth Session Security Reviewer
Works with the AI Agents you already use
Auth Session Security Reviewer
Security-focused code reviewer for JWT, OAuth, session management, and password storage vulnerabilities.
Free
Auth Session Security Reviewer
Example session with this skill installed
Review this JWT verification: const decoded = jwt.decode(token); if (decoded.user === 'admin') { allowAccess(); }
- Read your context and instructions
- Compiled the auth session security
CRITICAL: The code uses jwt.decode which only parses the payload without verifying the signature. An attacker can forge a token with {"user": "admin"} and gain full access. Use jwt.verify with a secret and explicitly pin the allowed algorithm (e.g., HS256) to prevent alg: none attacks.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Authentication bugs are high-stakes. A missing session regeneration call or a misconfigured JWT verification function is often the only thing standing between a secure app and a total account takeover.
What it does
- Identifies JWT vulnerabilities like
alg: noneexploits and symmetric/asymmetric algorithm confusion. - Checks session management for fixation risks and improper invalidation during logout.
- Audits password reset flows for token predictability, single-use enforcement, and user enumeration.
- Reviews password storage implementations to ensure use of slow hashes like Argon2 or bcrypt with unique salts.
- Scrutinizes OAuth/OIDC relying party code for
redirect_urivalidation andstateparameter integrity.
Why this beats prompting it yourself
Generic LLM reviews often provide vague best-practice advice. This skill focuses on demonstrable attack vectors, explaining exactly how a specific line of code enables an exploit so you can prioritize the fix. It follows a rigorous checklist derived from known failure patterns in JWT, OAuth, and session handling that generic prompts frequently overlook.
Use cases
- Reviewing a new JWT implementation to ensure tokens are securely signed, verified, and stored.
- Auditing a "forgot password" flow to prevent account enumeration and token hijacking.
- Checking login handlers for session fixation vulnerabilities before deployment.
- Verifying OAuth callback logic to ensure redirect URIs are properly locked down.
Known limitations
Cannot detect vulnerabilities in infrastructure-level auth (like WAF rules or VPC configs) if only application code is provided.
Does not audit infrastructure-level auth (WAF, VPC) unless config files are provided. Requires actual code or detailed flow descriptions for specific vulnerability demonstrations.
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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 2 months ago
- Free with an Agensi account