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 agentmods add skills/miru-zero/zero-brain/http2-specific-attacksnpx skills add miru-zero/zero-brain --skill http2-specific-attacksgit clone --depth 1 https://github.com/miru-zero/zero-brainWhat 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 | $0.00061 | $0.03212 |
| Opus 5 | $0.00030 | $0.01606 |
| Sonnet 5 | $0.00012 | $0.00642 |
| Haiku 4.5 | $0.00006 | $0.00321 |
Grade A, and why
http2-specific-attacks 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 yesterday.
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.
curl -v --http1.1 https://target.com/ \ This is a copy
92% identical to http2-specific-attacks — 4 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: HTTP/2 Specific Attacks — Expert Attack Playbook
AI LOAD INSTRUCTION: HTTP/2 protocol-level attack techniques beyond basic request smuggling. Covers h2c smuggling, pseudo-header manipulation, HPACK attacks, single-packet race conditions, and H2→H1 downgrade injection. Base models conflate HTTP/2 smuggling with HTTP/1.1 smuggling — this skill focuses on H2-unique attack surface.
0. RELATED ROUTING
- request-smuggling — CL.TE/TE.CL/TE.TE fundamentals and H2.CL/H2.TE variants
- request-smuggling/H2_SMUGGLING_VARIANTS.md — byte-level H2.CL/H2.TE payloads, CL.0, client-side desync
- race-condition — single-packet attack leverages H2 multiplexing for race conditions
- web-cache-deception — cache poisoning via H2 smuggled responses
1. HTTP/2 ATTACK SURFACE OVERVIEW
| Feature | Attack Surface |
|---|---|
| Binary framing | Frame-level manipulation, parser differentials |
| HPACK compression | Compression oracles (CRIME/BREACH), table poisoning |
| Multiplexing | Single-packet race conditions, RST_STREAM flood |
| Server push | Cache poisoning via unsolicited push |
Pseudo-headers (:method/:path/:authority/:scheme) |
Injection, request splitting, path discrepancy |
2. h2c (HTTP/2 CLEARTEXT) SMUGGLING
2.1 Concept
h2c is HTTP/2 without TLS, negotiated via the HTTP/1.1 Upgrade mechanism. Many reverse proxies forward the Upgrade: h2c header without understanding it, allowing attackers to bypass proxy-level access controls.
Client ──[Upgrade: h2c]──> Reverse Proxy ──[forwards blindly]──> Backend
│
Backend speaks H2
Proxy is blind to
the H2 conversation
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.
- yesterday First seen · 351 lines · 61 tokens per session scan A cd383f6aa09f
http2-specific-attacks is a skill published in the GitHub repository miru-zero/zero-brain (0 stars, last pushed 14d ago), licensed MIT. It adds 61 tokens to every session and 3,212 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 92% identical to http2-specific-attacks, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
planning-with-files-ar
تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.