agentmods.dev

ui-secure-review

ui-secure-review is a skill for Claude Code, Codex from LazyAGI/LazyMind. It costs 51 tokens per session (614 once invoked), scanned A, original, Apache-2.0.

A security-focused review for frontend and user-interface code. It looks for risks such as script injection, unsafe links, leaked tokens, missing checks on message origins, and client-side permission mistakes.

In plain words
What is it for?
Checking React, Vue, or JavaScript changes involving rendering, routing, authentication, browser storage, or API calls, and suggesting fixes and tests.
Why use it?
UI code often handles untrusted input, navigation, login state, and API data. Reviewing these paths can reveal ways an attacker might run code, steal data, or bypass controls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 589repo +73 yesterday A scan SkillSpector: pass 51 tokens original Apache-2.0

Good fit Checking React, Vue, or JavaScript changes involving rendering, routing, authentication, browser storage, or API calls, and suggesting fixes and tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lazyagi/lazymind/ui-secure-review
View source ↗ LazyAGI/LazyMind
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add LazyAGI/LazyMind --skill ui-secure-review
Clone the repo
git clone --depth 1 https://github.com/LazyAGI/LazyMind

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ui-secure-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/lazyagi/lazymind/ui-secure-review/github.svg)](https://agentmods.dev/skills/lazyagi/lazymind/ui-secure-review)
Your own site
<a href="https://agentmods.dev/skills/lazyagi/lazymind/ui-secure-review"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/ui-secure-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ui-secure-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/lazyagi/lazymind/ui-secure-review"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/ui-secure-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00614
Opus 5.5 $0.00020 $0.00246
Sonnet 5.5 $0.00010 $0.00123
Haiku 4.5 $0.00005 $0.00061

Measured 2mo ago against content hash 33c753c5d855, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui-secure-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/.curated/ui-secure-review/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Secure Review

Use this skill when the user asks for a frontend review with a security-first lens.

When to use

  • Reviewing PRs that touch UI rendering, routing, auth, storage, or API calls.
  • Auditing React, Vue, or plain JavaScript UI code for exploitable patterns.
  • Hardening existing UI code before release.

When not to use

  • Pure visual polish work with no logic or data handling changes.
  • Backend-only or infra-only changes.

Review workflow

  1. Map changed files and rank risk by feature type.
  2. Run quick pattern scans for dangerous APIs and sinks.
  3. Read high-risk files in detail and trace data from input to render.
  4. Confirm exploitability, impact, and realistic attack path.
  5. Report findings ordered by severity with exact file and line references.
  6. Suggest minimum safe fix and regression tests for each finding.

High-risk patterns to check

  • HTML injection: dangerouslySetInnerHTML, v-html, innerHTML, outerHTML.
  • Script execution: eval, new Function, string-based timers.
  • URL and navigation sinks: dynamic href, window.open, router redirects from untrusted params.
  • Tabnabbing risk: external links with target="_blank" missing rel="noopener noreferrer".
  • Token exposure: auth tokens in query params, logs, localStorage, or error traces.
  • Cross-origin trust: postMessage without strict origin and source checks.
  • Client-only authorization assumptions that can be bypassed in browser devtools.
  • Sensitive data persistence in cache, URL, or browser storage.

Quick scan commands

Use these patterns as a first pass, then manually verify context.

rg -n "dangerouslySetInnerHTML|v-html|innerHTML|outerHTML|eval\(|new Function\(" frontend/src
rg -n "window\.open|postMessage|target=\"_blank\"|localStorage|sessionStorage" frontend/src
rg -n "token|authorization|auth|redirect|location\.href|router\.push" frontend/src

Fix guidance

  • Prefer safe templating and escaped rendering over raw HTML insertion.
  • Validate and normalize all dynamic URLs before navigation.
  • Keep tokens in secure httpOnly cookies when architecture allows.
  • Add strict allowlists for cross-origin messaging and navigation targets.
  • Enforce authorization on the server even if UI hides actions.

Read the full file on GitHub · 58 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 58 lines · 51 tokens per session scan A 33c753c5d855

Subscribe to this mod's changes

ui-secure-review is a skill published in the GitHub repository LazyAGI/LazyMind (589 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 614 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

FrontendRAG and vectorsSecurityaiai-agentharnessworkworkflow
Related

ui-secure-review compared with skills from other repositories

ui-secure-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ui-secure-reviewLazyAGI/LazyMindSkill589yesterdayApache-2.0A51Claude Code, Codex
unified-llm-apiPrism-Shadow/penguin-harnessSkill3.2kyesterdayApache-2.0A43Claude Code, Codex
remote-compute-modalUnicomAI/wanwuSkill2.4k14d agoApache-2.0A65Claude Code, Codex
customizeUnicomAI/wanwuSkill2.4k14d agoApache-2.0A88Claude Code, Codex
smart-data-analysisUnicomAI/wanwuSkill2.4k14d agoApache-2.0A208Claude Code
claude-apiUnicomAI/wanwuSkill2.4k14d agoApache-2.0A84Claude Code, Codex
compute-env-setupUnicomAI/wanwuSkill2.4k14d agoApache-2.0A134Claude Code, Codex