CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-mobile-security-xss-scan

You are a frontend security specialist focusing on Cross-Site Scripting (XSS) vulnerability detection and prevention. Analyze React, Vue, Angular, and vanilla JavaScript code to identify injection poi

53

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/frontend-mobile-security-xss-scan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The content is highly actionable with executable detection code and tooling commands, but it is over-inlined for its length, repeats boilerplate, and lacks the validation checkpoints and file-split structure expected of a skill this size.

Suggestions

Move the full scanner class implementations into a ./references/ file (e.g. xss-scanner.ts) and keep SKILL.md as an overview that links to it, raising progressive_disclosure and conciseness.

Add an explicit validation step in the workflow (e.g., 'Triage each finding: confirm user-controlled input reaches the sink before reporting; re-run the scanner after fixes to verify resolution').

Trim the repeated persona line, the circular 'Use this skill when' bullets, and obvious explanations (e.g., that v-html renders raw HTML) that Claude already knows.

DimensionReasoningScore

Conciseness

The body is code-heavy and mostly earns its tokens, but it repeats the description's persona line, includes tautological boilerplate ('Working on xss vulnerability scanner for frontend code tasks'), and inlines full class scaffolding (XSSScanner, ReactXSSScanner, VueXSSScanner, SecureCodingGuide, XSSReportGenerator) that restates XSS basics Claude already knows.

3 / 5

Actionability

Provides concrete, largely copy-pasteable TypeScript detection logic plus runnable commands ('npm install --save-dev eslint-plugin-security', 'semgrep --config=p/xss --json'), with only minor gaps such as the scanner using fs.readFile without an import.

4 / 5

Workflow Clarity

Sections 1–6 give a clear sequence (detect → framework-specific → secure examples → automation → report → checklist), but there are no validation/verification checkpoints to triage false positives, which matters even for a read-only scanner producing findings.

3 / 5

Progressive Disclosure

Section headers are well-organized, but at ~322 lines the skill far exceeds the under-50-line simple-skill exception, inlines large reference-style code blocks that belong in separate files, and contains no external references at all.

3 / 5

Total

13

/

20

Passed

Description

61%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.

The description conveys a clear, specific niche with good trigger keywords, but it is truncated mid-sentence, written in penalized second-person voice, and lacks any explicit 'Use when...' trigger guidance.

Suggestions

Complete the truncated description and rewrite in third person ('Scans frontend code for...') instead of 'You are a frontend security specialist'.

Add an explicit 'Use when...' clause naming concrete user triggers (e.g., 'Use when reviewing React/Vue/Angular code for XSS, or when the user mentions injection, innerHTML, or dangerouslySetInnerHTML').

Keep the XSS/Cross-Site Scripting synonym pair and add common variations like 'sanitization', 'DOMPurify', and 'v-html' to round out trigger terms.

DimensionReasoningScore

Specificity

Names the XSS domain and several concrete actions ('vulnerability detection and prevention', 'Analyze React, Vue, Angular, and vanilla JavaScript code to identify injection poi'), but the second-person voice ('You are a frontend security specialist') triggers the -1 specificity penalty and the sentence is truncated mid-action.

3 / 5

Completeness

The 'what' is clear (XSS detection/prevention across frontend frameworks) but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Strong keyword coverage including the synonym pair 'Cross-Site Scripting (XSS)' plus 'React, Vue, Angular, JavaScript', 'vulnerability', and 'injection' — natural terms a user would say, with only minor variations missing.

4 / 5

Distinctiveness Conflict Risk

It carves a fairly distinct niche (client-side XSS scanning across specific frameworks) with minimal conflict risk, though 'frontend security' broadly could overlap with general security-scanning skills.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-skills
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.