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 tmolavi/mcp-agent-skills-hub --skill html-injection-testinggit clone --depth 1 https://github.com/tmolavi/mcp-agent-skills-hubWrote 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/tmolavi/mcp-agent-skills-hub/html-injection-testing)<a href="https://agentmods.dev/skills/tmolavi/mcp-agent-skills-hub/html-injection-testing"><img src="https://agentmods.dev/badge/skills/tmolavi/mcp-agent-skills-hub/html-injection-testing/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/tmolavi/mcp-agent-skills-hub/html-injection-testing"><img src="https://agentmods.dev/badge/skills/tmolavi/mcp-agent-skills-hub/html-injection-testing.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 | $0.00044 | $0.03481 |
| Opus 5 | $0.00022 | $0.01741 |
| Sonnet 5 | $0.00009 | $0.00696 |
| Haiku 4.5 | $0.00004 | $0.00348 |
Grade A, and why
html-injection-testing scanned grade A with 2 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 9d 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST -d "comment=<div style='color:red'>Malicious Content</div>" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "http://target.com/search?q=<h1>Test</h1>" This is a copy
86% identical to html-injection-testing — 14 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AUTHORIZED USE ONLY: Use this skill only for authorized security assessments, defensive validation, or controlled educational environments.
HTML Injection Testing
Purpose
Identify and exploit HTML injection vulnerabilities that allow attackers to inject malicious HTML content into web applications. This vulnerability enables attackers to modify page appearance, create phishing pages, and steal user credentials through injected forms.
Prerequisites
Required Tools
- Web browser with developer tools
- Burp Suite or OWASP ZAP
- Tamper Data or similar proxy
- cURL for testing payloads
Required Knowledge
- HTML fundamentals
- HTTP request/response structure
- Web application input handling
- Difference between HTML injection and XSS
Outputs and Deliverables
- Vulnerability Report - Identified injection points
- Exploitation Proof - Demonstrated content manipulation
- Impact Assessment - Potential phishing and defacement risks
- Remediation Guidance - Input validation recommendations
Core Workflow
Phase 1: Understanding HTML Injection
HTML injection occurs when user input is reflected in web pages without proper sanitization:
<!-- Vulnerable code example -->
<div>
Welcome, <?php echo $_GET['name']; ?>
</div>
<!-- Attack input -->
?name=<h1>Injected Content</h1>
<!-- Rendered output -->
<div>
Welcome, <h1>Injected Content</h1>
</div>
Key differences from XSS:
- HTML injection: Only HTML tags are rendered
- XSS: JavaScript code is executed
- HTML injection is often stepping stone to XSS
Attack goals:
- Modify website appearance (defacement)
- Create fake login forms (phishing)
- Inject malicious links
- Display misleading content
Phase 2: Identifying Injection Points
Map application for potential injection surfaces:
1. Search bars and search results
2. Comment sections
3. User profile fields
4. Contact forms and feedback
5. Registration forms
6. URL parameters reflected on page
7. Error messages
8. Page titles and headers
9. Hidden form fields
10. Cookie values reflected on page
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.
- 9d ago First seen · 505 lines · 44 tokens per session scan A e754642d59fa
html-injection-testing is a skill published in the GitHub repository tmolavi/mcp-agent-skills-hub (8 stars, last pushed 17d ago), licensed MIT. It adds 44 tokens to every session and 3,481 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). It is 86% identical to html-injection-testing, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
data-pro-skill
Market research data analysis meta-prompt. Transforms raw quantitative and qualitative data into dense, Tufte-style analytical documents. Document-driven. Invisible agent loop: Statistician -> Critic -> Tufte Designer. Commands: /dps-setup, /dps-cross, /dps-inject-open, /dps-export. Modes: /dps-mode:quant…
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
spark-video-cast
Scaffold and generate reference assets for characters (cast), locations (movie-set / set dressing), and key props — the three pillars of visual consistency in spark-video. Wraps bl image generate / edit for portrait creation. Use when adding new characters/locations/props or when costume/state changes are needed.
bailian-docs-llm-wiki
A searchable knowledge base for Alibaba Cloud Bailian, a platform for using and building applications with AI models. It contains model information, API documentation, application-development guides, multimodal features, and pricing details.
generate-plan-fact-report
Generates a plan-vs-actual report comparing planned and actual project data across three dimensions: timelines, budget, and scope (deliverables). Part of the Closing phase. Output feeds into generate-closure-report. Format: .md, manual data input via chat.
job-description-and-scorecard-builder
A hiring document generator that turns role notes into a job description and a matching interview scorecard. An interview scorecard is a set of criteria used to assess candidates consistently.