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/marcosd4h/DeepExtractRuntimenpx agentmods add skills/marcosd4h/deepextractruntime/ai-taint-scannerWrote 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/marcosd4h/deepextractruntime/ai-taint-scanner)<a href="https://agentmods.dev/skills/marcosd4h/deepextractruntime/ai-taint-scanner"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/ai-taint-scanner/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/marcosd4h/deepextractruntime/ai-taint-scanner"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/ai-taint-scanner.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 | $0.00077 | $0.03258 |
| Opus 5 | $0.00039 | $0.01629 |
| Sonnet 5 | $0.00015 | $0.00652 |
| Haiku 4.5 | $0.00008 | $0.00326 |
Grade A, and why
ai-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 9d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Taint Scanner
Purpose
Trace attacker-controlled data from entry points to dangerous sinks across module boundaries using LLM-driven analysis. The scanner builds a cross-module callgraph from attacker-reachable entry points, classifies every node (MUST_READ / KNOWN_API / TELEMETRY / LIBRARY), enriches each node with taint-specific metadata (sink density, parameter types, trust boundaries, assembly CFG summary), and delivers the enriched context to the AI agent in depth-level batches. The agent traces taint forward through each batch, returns requests for deeper functions, and reads deeper code itself via Shell -- iterating until max depth or taint termination.
This is NOT a pattern scanner. All taint propagation decisions are made by the LLM agent using the enriched callgraph context. A separate skeptic agent independently verifies each finding against assembly ground truth.
When to Use
- Trace attacker-controlled parameters from RPC/COM/export entry points to dangerous sinks (file writes, memory copies, privilege operations)
- Analyze cross-module data flow security across DLL boundaries
- Find where untrusted input reaches trust boundary crossings
- Identify parameter propagation chains from network-facing handlers to privileged operations
- AI-driven taint analysis on decompiled Windows binaries when deeper cross-module context is needed
When NOT to Use
- Memory corruption scanning (buffer overflows, UAF) -- use ai-memory-corruption-scanner
- 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
Data Sources
SQLite Databases (primary)
Individual analysis DBs in extracted_dbs/ provide the raw data:
functions.decompiled_code-- Hex-Rays decompiled C (read on demand)functions.assembly_code-- x64 assembly ground truth (read on demand)functions.simple_outbound_xrefs-- Callgraph edgesfunctions.function_signature-- Parameter types and namesfunctions.global_var_accesses-- Global variable reads/writesfunctions.loop_analysis-- Loop structure and complexityfile_info.exports-- Exported functionsfile_info.imports-- Imported APIsfile_info.entry_point-- PE entry points
What ships with it
6 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.
- 9d ago First seen · 316 lines · 77 tokens per session scan A f1ea8a53414f
ai-taint-scanner is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (19 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 3,258 once invoked, about $0.0004 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.