input-validation-and-sanitization

Use this skill when implementing any endpoint, form handler, CLI tool, or function that accepts external input. Validate and sanitize all untrusted data before processing — never assume input is safe.

Quality

92%

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

85%Weight 40%Scale 1-3

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

The body is concise, well-organized, and free of concept re-explanation, with one fully executable code example. The main gap is actionability: only the path-traversal section has copy-paste code while the other prevention categories rely on directives alone.

Suggestions

Add short executable code snippets for SQL-injection (a parameterized query) and XSS (an escaping helper) prevention, mirroring the path-traversal example so every category is copy-paste ready.

Include a brief verification step — e.g., a failing-input test case or an explicit length/regex assertion — so the skill shows how to confirm validation succeeded rather than only how to apply it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what SQL injection, XSS, or path traversal are, and every bullet earns its place without padding.	3 / 3
Actionability	Concrete directives are present and the path-traversal section includes a full executable code block, but the SQL-injection and XSS sections give only directives with no code examples, so guidance is concrete but incomplete rather than fully copy-paste ready.	2 / 3
Workflow Clarity	This is a simple, single-purpose skill under 50 lines with clear, well-organized bolded sections, so the simple-skills provision allows a top score even without an explicit multi-step workflow; no destructive/batch feedback-loop cap applies.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references (none of references/, scripts/, assets/ exist), and its well-organized bolded section headers satisfy the progressive-disclosure guideline for short skills.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

The description is exemplary: it states concrete contexts and actions, includes natural trigger terms, and explicitly covers both what the skill does and when to use it with a 'Use this skill when…' clause. It is clearly distinct from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete trigger contexts (endpoint, form handler, CLI tool, function) and specific actions ('Validate and sanitize all untrusted data before processing'), matching the score-3 anchor for multiple concrete actions rather than the partial score-2 example.	3 / 3
Completeness	Explicitly answers both what ('Validate and sanitize all untrusted data before processing') and when ('Use this skill when implementing any endpoint, form handler, CLI tool, or function…') with an explicit trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Uses natural terms a developer would actually say — 'endpoint', 'form handler', 'CLI tool', 'validate', 'sanitize', 'external input' — giving good coverage across contexts rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (input validation and sanitization) with distinct, concrete trigger contexts, making it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aiming-lab/MetaClaw
Path: memory_data/skills/input-validation-and-sanitization/SKILL.md
Commit: 922caf3

Reviewed: 9 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.