SKILL ISSUE

Security Review (affaan-m) vs Security Reviewer (jeffallan)

Security Review (affaan-m) and Security Reviewer (jeffallan) are both Security skills, so an agent choosing between them is matching on descriptions that overlap. Here is where they actually diverge.

Security Review

affaan-m/ecc

Helps developers implement secure features by listing concrete checks and recommended patterns for authentication, input handling, secret management, API endpoints, and payment or sensitive flows. Unlike similarly named tools that scan code or produce vulnerability audits, this one focuses on design-time guidance and implementation checklists — it does not run automated SAST, assign severity scores, or perform penetration-style audits of diffs.

1 scenario in the bank answer to it

Security Reviewer

jeffallan

Performs end-to-end security examinations of code, infrastructure, dependencies and secrets and compiles a prioritized audit report that assigns severity to each finding and lists concrete remediation steps. Unlike tools that only add inline comments, check authentication patterns, or scan a branch diff, this one is aimed at producing a compliance-aware, prioritized audit document rather than a quick pre-merge or single-file review.

1 scenario in the bank answer to it

What is the difference between Security Review (affaan-m) and Security Reviewer (jeffallan)?

Security Review (affaan-m)
Helps developers implement secure features by listing concrete checks and recommended patterns for authentication, input handling, secret management, API endpoints, and payment or sensitive flows. Unlike similarly named tools that scan code or produce vulnerability audits, this one focuses on design-time guidance and implementation checklists — it does not run automated SAST, assign severity scores, or perform penetration-style audits of diffs.
Security Reviewer (jeffallan)
Performs end-to-end security examinations of code, infrastructure, dependencies and secrets and compiles a prioritized audit report that assigns severity to each finding and lists concrete remediation steps. Unlike tools that only add inline comments, check authentication patterns, or scan a branch diff, this one is aimed at producing a compliance-aware, prioritized audit document rather than a quick pre-merge or single-file review.

Should I use Security Review (affaan-m) or Security Reviewer?

The clearest answer is a situation each one is unambiguously right for. Both of these are drawn from the game's question bank.

Reach for Security Review (affaan-m) when

I'm about to design a new login + payment flow and want a clear, practical list of secure patterns, do/avoid rules, and concrete checks I should follow as I build the feature so we don't bake in mistakes. I don't want someone to comb the whole repo for every weakness, produce a full cross-system compliance report, or only review a single outstanding change.

Winner: security-review-affaan-m gives the practical, design-time guidance this person needs — concrete patterns and checks for authentication, input handling, secret management, endpoints and sensitive flows to follow while writing the feature. What it does that the others do not is focus on implementation guidance up front rather than producing vulnerability scan results, a prioritized compliance audit, or a narrow review of a pending change. Most tempting wrong answer: security-review-getsentry — it finds and labels code-level problems, so it looks useful, but its output is about surfacing and scoring findings from existing source code rather than giving the developer a checklist of patterns and design-time rules to follow. (Other traps: security-reviewer-jeffallan would overdeliver a prioritized, compliance-style audit across code, infra and deps — useful but the wrong scope and heavier than needed; security-review-waybarrios only examines the specific unmerged change and focuses on high-confidence exploit paths, so it won't provide the broad, feature-level implementation guidance the author wants.)

Reach for Security Reviewer when

An auditor is coming and wants one document that grades the whole system — app code, servers, third-party libraries, leaked secrets — with a severity on every issue and a fix for each, ranked worst-first.

security-reviewer-jeffallan produces the end-to-end, severity-ranked audit document spanning code, infrastructure, dependencies and secrets. security-review-owasp and security-review-waybarrios only look at a diff or branch for exploits; security-review-affaan-m is build-time guidance, not an audit. The tell is a ranked document across the whole system.

What they have in common

Both are filed under Security, the axis along which they collide. That shared ground is what makes an agent pick between them on description alone — and what makes it pick wrong.

Nearby comparisons

Reading the difference is not the same as spotting it at speed. That is the game.

Today's session