CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

security-review

Security review checklist and patterns for adding authentication, handling user input, managing secrets, creating API endpoints, or implementing payment and sensitive features.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

63%Weight 40%Scale 1-5

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

A highly actionable, well-sectioned security checklist with abundant executable examples and validation checkpoints. Its weaknesses are token inefficiency from duplicated checklists and a single-file layout that inlines content (notably the blockchain section) that belongs in reference files, plus a couple of non-runnable code examples.

Suggestions

Deduplicate: fold the per-section 'Verification Steps' into the final pre-deployment checklist (or vice versa) and remove the 'When to Activate' section that restates the description.

Move the Solana/blockchain section and other topic deep-dives into references/ files linked from SKILL.md to cut context-window cost.

Fix non-executable examples: replace the @solana/web3.js `verify` import with the real nacl.sign.detached.verify API and note that `@/lib/csrf` is a to-be-implemented helper.

DimensionReasoningScore

Conciseness

The body is mostly lean code examples and checklists rather than concept explanations, but it is padded by redundancy: each of the ten sections ends with a 'Verification Steps' checklist that is then repeated almost item-for-item in the 'Pre-Deployment Security Checklist', the 'When to Activate' section restates the frontmatter description, and the closing 'Remember: Security is not optional' line is motivational filler. This fits 'mostly efficient but could be tightened' rather than the noticeably padded level 2.

3 / 5

Actionability

Concrete, mostly executable guidance throughout: zod validation schemas, parameterized query patterns, DOMPurify sanitization, Supabase RLS SQL, express-rate-limit config, and npm audit commands. Not 5 because a few examples are not runnable as written — `import { verify } from '@solana/web3.js'` is not a real export of that package, and the CSRF example imports a hypothetical `@/lib/csrf` module.

4 / 5

Workflow Clarity

Ten numbered checklist sections each paired with explicit 'Verification Steps' checkpoints, culminating in a consolidated pre-deployment checklist — clear structure with most checkpoints present. Not 5 because there is no explicit sequencing guidance (when to apply which section during a review) and no error-recovery loop beyond the static checklists.

4 / 5

Progressive Disclosure

The skill is a single ~490-line SKILL.md with no bundle files; sections are well-headered, so it is not a monolithic wall, but content that would naturally live in separate reference files (e.g., the niche Solana/blockchain section, per-topic deep dives) is inlined. This matches 'some structure but could be better organized; content that should be separate is inline'.

3 / 5

Total

14

/

20

Passed

Description

70%Weight 40%Scale 1-5

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 solid description with an explicit and concrete activation clause covering the right trigger domains. Its main weakness is a generic 'what' — 'checklist and patterns' names the artifact but not the actions the skill performs — and some missing natural synonyms such as 'authorization' and 'vulnerabilities'.

Suggestions

State the concrete actions the skill performs, e.g., 'Reviews code for hardcoded secrets, injection risks, and missing authorization checks; provides verification checklists.'

Add missing natural trigger terms such as 'authorization', 'login', 'vulnerabilities', and 'security audit'.

DimensionReasoningScore

Specificity

The phrase 'Security review checklist and patterns' names the domain and a single deliverable type but does not list several concrete actions (e.g., identifies hardcoded secrets, validates input handling, checks query parameterization). It matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive' — not 4 because no enumeration of specific actions is present.

3 / 5

Completeness

Both parts are present: 'what' ('Security review checklist and patterns') and an explicit 'when' clause ('for adding authentication, handling user input, managing secrets, creating API endpoints, or implementing payment and sensitive features') with concrete triggers. Not 5 because the 'what' is generic — it never states what the skill actually does with the checklist (review code, flag vulnerabilities).

4 / 5

Trigger Term Quality

Includes natural phrases users would say: 'adding authentication', 'handling user input', 'managing secrets', 'creating API endpoints', 'implementing payment'. A few common terms are missing (authorization, login, vulnerabilities, security audit), matching 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

The security-review niche is well defined with distinct trigger areas (secrets, payments, auth), giving minimal confusion risk; only minor overlap with a general code-review skill. Clear niche but not the fully distinct trigger set of a 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

affaan-m/ECC

Path

.agents/skills/security-review/SKILL.md

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.