triaging-an-unknown-sample

triaging-an-unknown-sample is a skill for Claude Code, Codex from meltedinhex/analyst-ai-pack. It costs 64 tokens per session (962 once invoked), scanned A, original, Apache-2.0.

A first-pass workflow for assessing an unknown or suspicious file without running it. It identifies the real file type, calculates hashes, checks reputation and packing, and reviews notable text inside the file.

In plain words
What is it for?
Use it to triage individual files or batches, record file details, rank suspicious samples, and prepare them for static or dynamic analysis.
Why use it?
It quickly separates files that need deeper investigation from those that can wait, while avoiding the risk of executing malware. The result is an initial assessment, not a final safety verdict.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to triage individual files or batches, record file details, rank suspicious samples, and prepare them for static or dynamic analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/meltedinhex/analyst-ai-pack/triaging-an-unknown-sample
Install

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.

Any agent
npx skills add meltedinhex/analyst-ai-pack --skill triaging-an-unknown-sample
Clone the repo
git clone --depth 1 https://github.com/meltedinhex/analyst-ai-pack

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for triaging-an-unknown-sample

README.md
[![agentmods](https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/triaging-an-unknown-sample/github.svg)](https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/triaging-an-unknown-sample)
Your own site
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/triaging-an-unknown-sample"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/triaging-an-unknown-sample/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.

agentmods 80×15 button for triaging-an-unknown-sample

Your own site · 80×15
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/triaging-an-unknown-sample"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/triaging-an-unknown-sample.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.00962
Opus 5 $0.00032 $0.00481
Sonnet 5 $0.00013 $0.00192
Haiku 4.5 $0.00006 $0.00096

Measured 9d ago against content hash b616173581db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

triaging-an-unknown-sample 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyst.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/triaging-an-unknown-sample/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triaging an Unknown Sample

When to Use

  • A suspicious file has arrived and you need to quickly decide whether it warrants deep static/dynamic analysis or can be dismissed.
  • You want a structured first-pass record (type, hashes, packing, notable strings) before committing analyst time.
  • You are batch-triaging many files and need to rank them by suspicion.

Do not use triage results as a final verdict. A clean string review or unknown reputation does not mean benign; it means proceed to deeper analysis.

Prerequisites

  • file (libmagic) for type identification, or the bundled magic-based detection.
  • Optional VirusTotal API key for reputation (hash lookups only — never upload someone else's data without authorization).
  • The sample in a neutralized, non-executable form inside the lab.

Safety & Handling

  • Triage is static: read bytes, never execute. Keep the sample with a neutralized extension.
  • Submit only the hash to reputation services unless you have authorization to upload the file itself; uploads can expose sensitive or attributable data.

Workflow

Step 1: Identify the true file type

Do not trust the extension. Identify by magic bytes:

python scripts/analyst.py triage sample.bin
# reports: detected type, magic, hashes, entropy, suspicious strings

A .pdf that is really a PE, or a .jpg that is a script, is itself a finding.

Step 2: Hash and check reputation

Compute the SHA-256 and look it up (hash-only) to see if it is known:

python scripts/analyst.py reputation --sha256 <sha256> --vt-key $VT_API_KEY

Known-bad with many detections → escalate. Unknown → continue triage; absence of detections is not exoneration.

Step 3: Estimate packing via entropy

High, uniform entropy across the whole file or a code section suggests packing or encryption:

entropy ~7.9 / 8.0 over most of the file  -> likely packed/encrypted
mixed entropy with readable strings       -> likely unpacked

Read the full file on GitHub · 120 lines

Files

What ships with it

3 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.

Changes

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.

  1. 9d ago First seen · 120 lines · 64 tokens per session scan A b616173581db

Subscribe to this mod's changes

triaging-an-unknown-sample is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 962 once invoked, about $0.0003 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 2026-09-03.

Related

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…

mukul975/Anthropic-Cybersecurity-Skills · 95 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…

mukul975/Anthropic-Cybersecurity-Skills · 73 tokens

analyzing-linux-elf-malware

Analyze malicious Linux ELF binaries — botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure — through static analysis, dynamic tracing, and reverse engineering of x8664 and ARM samples. Use when investigating Linux malware, triaging a suspicious ELF binary…

mukul975/Anthropic-Cybersecurity-Skills · 82 tokens

dynamic-malware-analysis

Execute and analyze malware samples within a highly controlled, instrumented sandbox environment to observe their true behavior, network communications, file system modifications, and registry changes in real-time.

ShulkwiSEC/bb-huge · 41 tokens

analyzing-malicious-pdf-with-peepdf

A Chinese-language skill for examining suspicious PDF files with peepdf, pdfid, and pdf-parser. It is intended for static malware analysis, which studies a file without running it.

killvxk/cybersecurity-skills-zh · 50 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.

26zl/cybersec-toolkit · 43 tokens