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 tranhieutt/software_development_department --skill markdown-injection-scannergit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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/tranhieutt/software_development_department/markdown-injection-scanner)<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/markdown-injection-scanner"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/markdown-injection-scanner/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/tranhieutt/software_development_department/markdown-injection-scanner"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/markdown-injection-scanner.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 | $0.00058 | $0.02683 |
| Opus 5 | $0.00029 | $0.01341 |
| Sonnet 5 | $0.00012 | $0.00537 |
| Haiku 4.5 | $0.00006 | $0.00268 |
Grade A, and why
markdown-injection-scanner scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 16 | Shell Command Injection | `(curl\s+\|wget\s+\|bash\s+-c\|sh\s+-c\|powershell\|cmd\.exe\|/bin/sh\|/bin/bash\|rm\s+-rf\|chmod\s+777\|sudo\s+)` | Shell command execution | How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Injection Scanner
Scans all .md files in a target directory for 18 categories of malicious code injection.
Uses regex pattern matching across the entire file corpus with parallel subagent execution for speed.
Usage
/markdown-injection-scanner [target-directory]
If no directory is specified, ask the user to provide one.
Phase 1: Discovery — Map the File Corpus
-
Count all .md files in target directory (recursive).
-
Sample 2-3 files to understand the file structure and content type (design docs, documentation, config, etc.).
-
Report file count and content type before proceeding.
Phase 2: Parallel Injection Scanning
Execute scans in 3 parallel batches using subagents for speed. Each subagent uses search_files with the target directory path and *.md file pattern.
Batch 1 — Script and Code Injection (5 patterns)
| # | Category | Regex Pattern | Threat |
|---|---|---|---|
| 1 | Script tags | <script[^>]*> |
Embedded JavaScript execution |
| 2 | HTML Event Handlers | (onclick|onerror|onload|onmouseover|onfocus|onblur|onresize|onsubmit|onchange|oninput|onkeydown|onkeyup|onkeypress|ontouchstart|onmouseenter|onmouseleave)\s*= |
Inline JS via HTML attributes |
| 3 | JS/VBScript Protocol | (javascript:|vbscript:) |
Malicious link protocols |
| 4 | Dynamic Code Execution | (eval\s*\(|Function\s*\(|setTimeout\s*\(|setInterval\s*\() |
Code execution via eval/setTimeout |
| 5 | DOM Manipulation | (document\.(cookie|domain|write)|window\.(location|open)|XMLHttpRequest|fetch\s*\() |
DOM-based attacks |
Batch 2 — Obfuscation and Encoding (6 patterns)
| # | Category | Regex Pattern | Threat |
|---|---|---|---|
| 6 | Base64 Payloads | (base64|atob|btoa|b64decode|b64encode)[\s(] |
Encoded malicious content |
| 7 | Data URI Injection | data:\s*(text/html|application/javascript|text/javascript) |
Inline HTML/JS via data URIs |
| 8 | SVG Injection | <svg[^>]*> |
SVG-based XSS vectors |
| 9 | Hex/Unicode Encoding | (\\x[0-9a-fA-F]{2}|\\u[0-9a-fA-F]{4}|&#x[0-9a-fA-F]+;) |
Obfuscated character encoding |
| 10 | Hidden Text — display:none | <(span|div|p)[^>]*style\s*=\s*['"][^'"]*display\s*:\s*none |
Hidden content tricks |
| 11 | Hidden Text — font-size:0 | font-size\s*:\s*0 |
Invisible text |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 189 lines · 58 tokens per session scan A cd48c8826f33
markdown-injection-scanner is a skill published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 2,683 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
serena
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
database-migrations
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
tdd
Strict test-driven development for behavior changes. Requires verified RED before production code, minimal GREEN, and refactor only after passing tests.
verify
Fresh verification gate before claiming done, fixed, passing, ready, or before commit/PR. Evidence before claims, always.