CtrlK
BlogDocsLog inGet started
Tessl Logo

security-review

Skill do Security Reviewer para auditoria de segurança e boas práticas. Use quando precisar revisar código para vulnerabilidades, validar implementação de auth, checar OWASP Top 10, revisar CORS/CSRF/XSS, garantir DRY e clean code, ou qualquer review de segurança. Trigger em: "segurança", "security review", "vulnerabilidade", "OWASP", "XSS", "CSRF", "CORS", "injection", "HttpOnly", "cookie seguro", "DRY", "code review", "boas práticas", "audit", "pentest", "sanitização".

63

Quality

75%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/06-security-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The skill provides highly actionable, concrete security review guidance with executable code examples and detailed checklists, which is its strongest quality. However, it suffers significantly from verbosity — inlining the entire OWASP Top 10 checklist, full code examples, DRY/SOLID principles, and dependency management guidance makes it a monolithic document that wastes tokens on content that should be in referenced files. The review workflow itself lacks a clear step-by-step sequence for how to actually conduct the review.

Suggestions

Move the detailed OWASP Top 10 checklists, code examples (headers, CORS, CSRF, XSS), and DRY/SOLID checklists into referenced files (e.g., docs/owasp-checklist.md, docs/security-headers.md) and keep only a brief summary with links in SKILL.md

Remove explanations of well-known concepts (SOLID acronym expansion, what DRY means, what each OWASP category is) — Claude already knows these; just provide the project-specific checklist items

Add an explicit numbered workflow for conducting a security review (e.g., 1. Receive diffs → 2. Run automated checks → 3. Manual OWASP review → 4. Generate report → 5. Validate findings → 6. Handoff decision)

Remove the 'Código Limpo' section which duplicates content already covered in the DRY/Clean Code checklist above it

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~300+ lines. It explains concepts Claude already knows (SOLID principles, what DRY means, what XSS is), includes full OWASP Top 10 checklists that could be referenced externally, and has redundant sections (e.g., 'Código Limpo' repeats what's already in the DRY checklist). The anti-rationalization table and governance preamble add significant token overhead.

1 / 3

Actionability

The skill provides fully executable TypeScript code examples for security headers, CORS configuration, CSRF protection, and XSS prevention. Checklists are concrete with specific values (bcrypt cost >= 12, JWT 15 min max, RS256). The report template is copy-paste ready with clear structure.

3 / 3

Workflow Clarity

The handoff criteria are clear (5 conditions before releasing to Deployer), and the report template provides a structured output. However, the overall review workflow lacks explicit sequencing — there's no clear 'Step 1, Step 2, Step 3' process for conducting the review itself, and validation/verification checkpoints during the review process are implicit rather than explicit.

2 / 3

Progressive Disclosure

References to external files exist (docs/skill-guides/security-review.md, personas/security-auditor.md, various policies), but the SKILL.md itself is monolithic — the full OWASP Top 10 checklists, all code examples, DRY/SOLID/Clean Code checklists, and dependency management guidance are all inline when they could be in referenced files. The skill tries to be both overview and detailed reference simultaneously.

2 / 3

Total

8

/

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.

This is a strong skill description that clearly defines its security review and auditing purpose with specific capabilities, explicit trigger guidance, and comprehensive bilingual trigger terms. It follows the recommended pattern of stating what it does, when to use it, and providing natural keywords. The only minor note is the inclusion of 'DRY' and 'clean code' which slightly broadens scope beyond pure security, but these are well-contextualized within the security review framing.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: revisar código para vulnerabilidades, validar implementação de auth, checar OWASP Top 10, revisar CORS/CSRF/XSS, garantir DRY e clean code. These are clearly defined, actionable capabilities.

3 / 3

Completeness

Clearly answers both 'what' (security auditing, vulnerability review, auth validation, OWASP checks, clean code enforcement) and 'when' with an explicit 'Use quando...' clause and a dedicated 'Trigger em:' list providing explicit trigger guidance.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms in both Portuguese and English: 'segurança', 'security review', 'vulnerabilidade', 'OWASP', 'XSS', 'CSRF', 'CORS', 'injection', 'HttpOnly', 'cookie seguro', 'DRY', 'code review', 'boas práticas', 'audit', 'pentest', 'sanitização'. These are terms users would naturally use when requesting security reviews.

3 / 3

Distinctiveness Conflict Risk

Clearly occupies a distinct niche of security auditing and review. The specific security-focused triggers (OWASP, XSS, CSRF, injection, pentest, sanitização) are unlikely to conflict with general code review or other development skills.

3 / 3

Total

12

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Repository
felvieira/claude-skills-fv
Reviewed

Table of Contents

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.