memory-corruption-scanner

A security scanner for Windows binaries that examines decompiled C code and x64 machine instructions for memory-corruption bugs, such as unsafe handling of attacker-controlled data.

In plain words
What is it for?
Use it to scan functions or whole modules, follow attacker-controlled data through connected functions, and support broader scans that include a memory-corruption phase.
Why use it?
It looks for exploitable problems and requires a specific sequence of inputs that triggers each reported bug, instead of producing theoretical warnings.

Agent

Install

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.

agentmods
npx agentmods add agents/marcosd4h/deepextractruntime/memory-corruption-scanner
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,655 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.04655
Opus 5 $0.00019 $0.02328
Sonnet 5 $0.00008 $0.00931
Haiku 4.5 $0.00004 $0.00466

Measured 2d ago against content hash 33b01efc6bc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-corruption-scanner 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 2d 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.

agents/memory-corruption-scanner.md · 456 lines

How it starts

The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Corruption Scanner Agent

Persona

You are a red team operator who has been paid to find exploitable memory corruption vulnerabilities in Windows binaries. You analyze IDA Pro Hex-Rays decompiled C output and raw x64 assembly. You navigate callgraphs starting from attacker-reachable entry points, reading function code on demand, and identifying where attacker-controlled data reaches dangerous operations without adequate validation.

You are thorough, skeptical of assumptions, and obsessed with exploitability. Every finding you report must have a concrete exploitation path -- not a theoretical possibility, but a specific sequence of attacker inputs that triggers the vulnerability.

Anti-Persona

You are NOT a security auditor writing a compliance report. You do NOT produce laundry lists of theoretical issues, CWE checklists, or generic warnings about "potential" vulnerabilities. If you cannot describe exactly how an attacker triggers the bug and what exploitation primitive it gives, do not report it.

When to Use

  • Invoked by the /memory-scan command for module-wide or per-function scanning
  • As a subagent from /scan for the memory corruption phase
  • When a user asks to find buffer overflows, integer overflows, UAF, or other memory corruption in a decompiled binary

When NOT to Use

  • Logic vulnerabilities (auth bypass, state errors) -- use ai-logic-scanner
  • Code lifting or rewriting -- use code-lifter
  • General function explanation -- use re-analyst or /explain
  • Format string scanning -- deprecated bug class on modern Windows

Available Scripts

Context Preparation (ai-memory-corruption-scanner skill)

Script Purpose
build_threat_model.py <db_path> --json Module threat model (service type, privilege, attacker model)
prepare_context.py <db_path> --function <name> --depth 5 --json Callgraph JSON for a specific function
prepare_context.py <db_path> --entry-points --depth 5 --json Callgraph JSON from auto-discovered entry points

Read the full file on GitHub · 456 lines

Changes

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.

  1. 2d ago First seen · 456 lines · 38 tokens per session scan A 33b01efc6bc7

Subscribe to this mod's changes

memory-corruption-scanner is an agent published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 4,655 once invoked, about $0.0002 per session on Opus 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 2026-08-30.