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 ShulkwiSEC/bb-huge --skill injection-checkinggit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/shulkwisec/bb-huge/injection-checking)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/injection-checking"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/injection-checking/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/shulkwisec/bb-huge/injection-checking"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/injection-checking.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 | $0.00050 | $0.00597 |
| Opus 5 | $0.00025 | $0.00298 |
| Sonnet 5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
injection-checking 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 7d 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
100% identical to injection-checking — 0 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.
What it actually says
Injection Testing Router
This is the routing entry point when input reaches a dangerous interpreter or execution environment.
After confirming this is an injection-class issue, use it to decide whether it is mainly browser context, database, template engine, server-side requests, XML parsing, or system commands.
When to Use
- Input reaches HTML, JS, SQL, templates, URL fetchers, XML parsers, or shell
- You have not yet decided whether to start with XSS, SQLi, SSRF, XXE, SSTI, CMDi, or NoSQL
- You need to choose the correct deep-topic skill based on input flow
Skill Map
- XSS Cross Site Scripting
- SQLi SQL Injection
- SSRF Server Side Request Forgery
- XXE XML External Entity
- SSTI Server Side Template Injection
- CMDi Command Injection
- NoSQL Injection
- Deserialization Insecure
- JNDI Injection
- Expression Language Injection
- CRLF Injection
- Extra Injection Types (SSI, LDAP, XPath)
- Request Smuggling
- Prototype Pollution
- Type Juggling
- HTTP Parameter Pollution
- XSLT Injection
- CSV Formula Injection
Recommended Flow
- First identify the final sink of the input
- Then choose the topic skill that best matches that interpreter
- Small payload samples and quick triage are merged into each main skill; no extra payload router is needed
Related Categories
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.
- 7d ago First seen · 50 lines · 50 tokens per session scan A 5a6d03027213
injection-checking is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 597 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to injection-checking, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
skill-debug
Debug a reproducible symptom with a bounded feedback loop and original-scenario verification.
debug
Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-implement. NOT a feature to spec or build (that is specify/implement), NOT the lint/test gate (that is verify), NOT adversarial diff…
pwn-ai-agent-reflect
Drive PWN::AI::Agent::Reflect from pwneval.
pwn-ai-agent-transparentbrowser
Drive PWN::AI::Agent::TransparentBrowser from pwneval.
continuum-observability
Trace agent runs with Langfuse, decorate functions with @observe, collect latency/token/error metrics, and report errors. Invoke when the user asks about "see what the LLM was prompted with", "Langfuse traces", "track latency", "metrics dashboard", "error reporting", or "instrument my function".
pwn-ai-agent-tools-debuglane
Drive PWN::Ai::Agent::Tools::DebugLane from pwneval.