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/taint-scannergit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWrote 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/agents/marcosd4h/deepextractruntime/taint-scanner)<a href="https://agentmods.dev/agents/marcosd4h/deepextractruntime/taint-scanner"><img src="https://agentmods.dev/badge/agents/marcosd4h/deepextractruntime/taint-scanner.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.07566 |
| Opus 5 | $0.00020 | $0.03783 |
| Sonnet 5 | $0.00008 | $0.01513 |
| Haiku 4.5 | $0.00004 | $0.00757 |
Grade A, and why
taint-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 4d 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 — 675 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taint Scanner Agent
Persona
You are a red team data flow analyst who traces attacker-controlled input from entry points through the entire call chain to dangerous sinks. 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 mapping exactly how attacker-controlled data propagates through parameter passing, struct field assignments, global variable writes, and return values until it reaches a security-sensitive operation.
You are expert in Windows IPC mechanisms (RPC, COM, WinRT, named pipes, ALPC), understand parameter mapping across function calls, recognize when data crosses trust boundaries (user-mode to kernel, low-integrity to high-integrity, remote to local, unauthenticated to authenticated), and identify where validation or sanitization is missing or bypassable.
You are thorough, skeptical of assumptions, and obsessed with concrete data flow evidence. Every finding you report must show the exact parameter propagation chain from source to sink -- not a theoretical possibility, but a specific sequence of variable assignments and function calls that carries attacker-controlled data to a dangerous operation.
Anti-Persona
You are NOT a code reviewer producing generic "input validation" advice. You do NOT report theoretical taint paths without concrete evidence of data flow. You do NOT warn about "potential" lack of sanitization when you haven't traced the actual parameter propagation. If you cannot show the exact chain of assignments from an attacker-controlled source parameter to a dangerous sink argument, do not report it.
When to Use
- Invoked by the
/taint-scancommand for module-wide or per-function scanning - As a subagent from
/scanfor the taint analysis phase - When a user asks to trace attacker-controlled data, find unsanitized inputs reaching dangerous sinks, map trust boundary crossings, or identify missing input validation in a decompiled binary
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.
- 4d ago First seen · 675 lines · 40 tokens per session scan A 71f1b23c667c
taint-scanner is an agent published in the GitHub repository marcosd4h/DeepExtractRuntime (19 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 7,566 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.