aif-security-checklist

Security audit checklist based on OWASP Top 10 and best practices. Covers authentication, injection, XSS, CSRF, secrets management, and more. Use when reviewing security, before deploy, asking "is this secure", "security check", "vulnerability".

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and well-structured with sound progressive disclosure, but held back by redundant client-logging guidance and a destructive git-cleanup workflow that omits an explicit validation checkpoint.

Suggestions

Consolidate the client-facing logging/error guidance into one location and cross-reference it from the Pre-Deployment Checklist and Quick Audit Commands to remove triplication.

Add an explicit validation/checkpoint step to the git history cleanup workflow (e.g., verify the secret is gone with `git log -p` / a secret-scanner re-scan before the force-push) to satisfy the destructive-operation feedback-loop requirement.

Trim the Config/language section to the resolved-value defaults and the translation-preserve list, moving the detailed legacy-value handling into a reference if needed.

Dimension	Reasoning	Score
Conciseness	Mostly efficient checklists and code, but the client logging/error guidance recurs across the Pre-Deployment Checklist, API Security "Client-Facing Logging & Errors", and Quick Audit Commands, and the Config/language section is verbose; it is not 3 because of this redundancy and padding, and not 1 because the bulk is actionable rather than conceptual explanation.	2 / 3
Actionability	Provides executable code (parameterized queries, zod validation, helmet headers), concrete commands (grep patterns, npm audit, git filter-branch), and ❌/✅ examples that are copy-paste ready, matching the top anchor.	3 / 3
Workflow Clarity	The ignore flow is a clear 4-step sequence with a confirm step and the audit flow is sequenced, but the destructive git-history cleanup and force-push batch operation lacks an explicit validation checkpoint, which caps this at 2 per the rubric's destructive-operation feedback-loop note.	2 / 3
Progressive Disclosure	Deep material is split into one-level-deep, clearly signaled real references (AUTH-PATTERNS.md, RACE-CONDITIONS.md, PROMPT-INJECTION.md) plus scripts/audit.sh, all of which exist, while the body stays an organized overview with sectioned navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete capability list, explicit "Use when" triggers, and a distinct security-audit niche. No vagueness or over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capability areas — "Covers authentication, injection, XSS, CSRF, secrets management, and more" — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("Security audit checklist based on OWASP Top 10 and best practices") and when ("Use when reviewing security, before deploy...") with an explicit trigger clause, matching the top anchor.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would actually say — "reviewing security", "before deploy", "is this secure", "security check", "vulnerability" — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (security auditing) with distinct, security-specific triggers unlikely to fire for unrelated skills; it is not below 3 because no overlap with sibling skills is implied, and not below by virtue of being broadly but precisely scoped.	3 / 3
	Total	12 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (610 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-security-checklist/SKILL.md
Commit: 4b943ec

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.