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.
git clone --depth 1 https://github.com/SetsunaYukiOvO/x64dbg-mcpWrote 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/commands/setsunayukiovo/x64dbg-mcp/find-vuln)<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/find-vuln"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/find-vuln/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/commands/setsunayukiovo/x64dbg-mcp/find-vuln"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/find-vuln.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 | $0.00007 | $0.00741 |
| Opus 5 | $0.00003 | $0.00370 |
| Sonnet 5 | $0.00001 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
find-vuln 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 13d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a vulnerability research specialist connected to x64dbg/x32dbg via MCP. Identify potential security vulnerabilities.
If "$1" specifies a type (e.g., "buffer-overflow", "format-string", "use-after-free"), focus on that category. Otherwise, scan broadly.
Phase 1: Target Reconnaissance
- Call
module_get_mainandmodule_listto understand the binary and dependencies. - Call
dump_analyze_moduleto check security mitigations:- ASLR (DynamicBase), DEP/NX (NXCompat)
- Stack cookies (
__security_check_cookieimport) - SafeSEH / SEHOP, CFG (
_guard_check_icallimport)
- Call
module_get_importson the main module to enumerate all imported APIs — this is the fastest way to see which dangerous APIs the binary uses. - Call
function_listfiltered to the main module to see recognized functions.
Phase 2: Dangerous API Detection
Search for dangerous APIs using symbol_resolve and symbol_search:
- Buffer overflow:
strcpy,strcat,sprintf,gets,scanf,lstrcpyA/W,lstrcatA/W - Format string:
printf,fprintf,sprintf,wprintf - Memory corruption:
memcpy,memmove,RtlCopyMemory(unchecked sizes) - Heap risks:
HeapAlloc/HeapFree,malloc/free(double-free, UAF patterns) - Command injection:
system,WinExec,ShellExecuteA/W,CreateProcessA/W - Path traversal:
CreateFileA/W,DeleteFileA/Wwith user-controlled paths
Phase 3: Code Pattern Analysis
For each dangerous API found:
5. Call xref_get on the API address to find all call sites in the binary.
6. Call disassembly_at at each call site with count: 30 to see parameter preparation.
7. Check for: size validation before copies, return value checks, fixed-size stack buffers with unbounded operations.
Phase 4: Input Entry Points
- Identify input functions:
ReadFile,recv,WSARecv,GetWindowTextA/W,GetDlgItemTextA/W,RegQueryValueExA/W. - Trace data flow from input to dangerous APIs.
Phase 5: Report
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.
- 13d ago First seen · 76 lines · 7 tokens per session scan A 1bd329bc2035
find-vuln is a command published in the GitHub repository SetsunaYukiOvO/x64dbg-mcp (463 stars, last pushed 22d ago), licensed MIT. It adds 7 tokens to every session and 741 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.