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 agents/marcosd4h/deepextractruntime/memory-corruption-scannergit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWhat 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 | $0.00038 | $0.04655 |
| Opus 5 | $0.00019 | $0.02328 |
| Sonnet 5 | $0.00008 | $0.00931 |
| Haiku 4.5 | $0.00004 | $0.00466 |
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.
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-scancommand for module-wide or per-function scanning - As a subagent from
/scanfor 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 |
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.
- 2d ago First seen · 456 lines · 38 tokens per session scan A 33b01efc6bc7
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.