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.
npx skills add LiHongwei-cn/lihongwei-cn --skill top-web-vulnerabilitiesgit clone --depth 1 https://github.com/LiHongwei-cn/lihongwei-cnWrote 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.
[](https://agentmods.dev/skills/lihongwei-cn/lihongwei-cn/top-web-vulnerabilities)<a href="https://agentmods.dev/skills/lihongwei-cn/lihongwei-cn/top-web-vulnerabilities"><img src="https://agentmods.dev/badge/skills/lihongwei-cn/lihongwei-cn/top-web-vulnerabilities/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.
<a href="https://agentmods.dev/skills/lihongwei-cn/lihongwei-cn/top-web-vulnerabilities"><img src="https://agentmods.dev/badge/skills/lihongwei-cn/lihongwei-cn/top-web-vulnerabilities.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.05213 |
| Opus 5 | $0.00023 | $0.02606 |
| Sonnet 5 | $0.00009 | $0.01043 |
| Haiku 4.5 | $0.00005 | $0.00521 |
Grade A, and why
top-web-vulnerabilities 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 8d 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.
This is a copy
97% identical to top-web-vulnerabilities — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Top 100 Web Vulnerabilities Reference
Purpose
Provide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic vulnerability identification, impact assessment, and remediation guidance across the full spectrum of web security threats. Content organized into 15 major vulnerability categories aligned with industry standards and real-world attack patterns.
Prerequisites
- Basic understanding of web application architecture (client-server model, HTTP protocol)
- Familiarity with common web technologies (HTML, JavaScript, SQL, XML, APIs)
- Understanding of authentication and authorization concepts
- Access to web application security testing tools (Burp Suite, OWASP ZAP)
- Knowledge of secure coding principles recommended
Outputs and Deliverables
- Complete vulnerability catalog with definitions, root causes, impacts, and mitigations
- Category-based vulnerability groupings for systematic assessment
- Quick reference for security testing and remediation
- Foundation for vulnerability assessment checklists and security policies
Core Workflow
Phase 1: Injection Vulnerabilities Assessment
Evaluate injection attack vectors targeting data processing components:
SQL Injection (1)
- Definition: Malicious SQL code inserted into input fields to manipulate database queries
- Root Cause: Lack of input validation, improper use of parameterized queries
- Impact: Unauthorized data access, data manipulation, database compromise
- Mitigation: Use parameterized queries/prepared statements, input validation, least privilege database accounts
Cross-Site Scripting - XSS (2)
- Definition: Injection of malicious scripts into web pages viewed by other users
- Root Cause: Insufficient output encoding, lack of input sanitization
- Impact: Session hijacking, credential theft, website defacement
- Mitigation: Output encoding, Content Security Policy (CSP), input sanitization
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.
- 8d ago First seen · 548 lines · 47 tokens per session scan A b8fe9016ffc8
top-web-vulnerabilities is a skill published in the GitHub repository LiHongwei-cn/lihongwei-cn (5 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 5,213 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to top-web-vulnerabilities, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
law-of-common-region
Apply the Law of Common Region — a shared container, background, or border groups elements regardless of spacing. Use when grouping must survive a tight layout. For grouping by spacing alone, use law-of-proximity.
critique-visual-hierarchy
Critique a rendered screen's hierarchy — entry point, eye flow, weight distribution, and emphasis. Use when attention lands in the wrong place. For establishing hierarchy in new work, use visual-hierarchy (ui-design).
presentation-deck
Structure a design presentation for a specific audience and decision. Use when presenting internally. For a portfolio narrative use case-study; for the written argument use design-rationale.
accessibility-test-plan
Plan accessibility testing — assistive technologies, participant criteria, WCAG coverage, and session protocol. Use when scheduling testing with real AT users. Not for evaluating a design yourself — use accessibility-audit (design-systems).