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 skills/fire3/aida-audit/aida-cli-mcp-attack-surface-analysisnpx skills add fire3/aida-audit --skill aida-cli-mcp-attack-surface-analysisgit clone --depth 1 https://github.com/fire3/aida-auditWrote 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/fire3/aida-audit/aida-cli-mcp-attack-surface-analysis)<a href="https://agentmods.dev/skills/fire3/aida-audit/aida-cli-mcp-attack-surface-analysis"><img src="https://agentmods.dev/badge/skills/fire3/aida-audit/aida-cli-mcp-attack-surface-analysis.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 | $0.00019 | $0.03296 |
| Opus 5 | $0.00010 | $0.01648 |
| Sonnet 5 | $0.00004 | $0.00659 |
| Haiku 4.5 | $0.00002 | $0.00330 |
Grade A, and why
aida-audit-attack-surface-analysis 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 5d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDA MCP Attack Surface Analysis Skill Guide
This document guides agents on how to use the AIDA MCP toolset to perform Code Attack Surface Analysis. It focuses on finding source points (untrusted external input entering the program) as the first and most critical step, then connecting sources to sinks to form candidate exploit chains. It also prescribes a standardized reporting format.
1. Core Concepts
- Attack Surface: The sum of all paths for data/commands into and out of the application, and the code that protects these paths.
- Source Point (Source): Any program point that introduces untrusted external data into the process (network reads, file reads, environment variables, IPC/RPC messages, CLI args, registry/config, etc.).
- Entry Point (Control Entry): A control-flow entry into the binary from the outside (exports, callbacks, RPC dispatchers, message handlers). Entry points often contain sources, but they are not the same concept.
- Sink: A sensitive operation that becomes dangerous when influenced by untrusted input (command execution, file writes, dynamic code loading, unsafe memory operations, risky deserialization).
- Reachability: Whether a sink is reachable from a source through a realistic call path and data-flow path.
- Evidence Standard: Every claim in the report must be backed by a tool output snippet (pseudocode, xrefs, strings entry, etc.) and a concrete location (function name + address).
2. Skill Patterns
2.1 Project Triage (Always First)
Goal: Establish scope and pick targets.
- Get project overview:
get_project_overview() - List binaries:
get_project_binaries(offset=0, limit=50, detail=true) - Pick a binary and get metadata:
get_binary_metadata(binary_name)- Use metadata to determine platform hints (PE/ELF), architecture, and whether strings/imports/xrefs are available.
2.2 Source Point Discovery (Primary Best Practice)
Goal: Find where untrusted data enters the process. Start from the most common real-world sources: network input, file input, environment/CLI input, IPC/RPC, then use data features (strings, magic numbers, protocol markers) to accelerate.
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.
- 5d ago First seen · 189 lines · 19 tokens per session scan A d3bef5fa8a4b
aida-audit-attack-surface-analysis is a skill published in the GitHub repository fire3/aida-audit (5 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 3,296 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
ctf-pwn
Solve CTF binary exploitation challenges by discovering and exploiting memory corruption vulnerabilities to read flags. Use for buffer overflows, format strings, heap exploits, ROP challenges, or any pwn/exploitation task.
deep-analysis
Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming…
ctf-rev
Solve CTF reverse engineering challenges using systematic analysis to find flags, keys, or passwords. Use for crackmes, binary bombs, key validators, obfuscated code, algorithm recovery, or any challenge requiring program comprehension to extract hidden information.
pyghidra-scripting
Write and run Python (PyGhidra) code inside the Ghidra session that ReVa's MCP server is already attached to, using the five ReVa scripting tools — run-script, list-scripts, read-script, write-script, edit-script. Use this whenever the user asks to execute Python against the current program, reach for the Ghidra Flat…
ctf-crypto
Solve CTF cryptography challenges by identifying, analyzing, and exploiting weak crypto implementations in binaries to extract keys or decrypt data. Use for custom ciphers, weak crypto, key extraction, or algorithm identification.