What is triage-malware?

A guide for investigating a suspicious file by its MD5, SHA1, or SHA256 fingerprint, a value used to identify a file.

Use it to review the file’s malware classification and behavior, find affected hosts, collect network indicators, and recommend containment.

It combines malware-report, behavior, network, and execution evidence to show whether the file affected systems and what it did.

triage-malware — Skill for Claude Code and Codex by dandye/ai-runbooks

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 dandye/ai-runbooks --skill triage-malware

Clone the repo

git clone --depth 1 https://github.com/dandye/ai-runbooks

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dandye/ai-runbooks/triage-malware/github.svg)](https://agentmods.dev/skills/dandye/ai-runbooks/triage-malware)

Your own site

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/triage-malware"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/triage-malware/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/triage-malware"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/triage-malware.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,193 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01193
Opus 5.5	$0.00019	$0.00477
Sonnet 5.5	$0.00010	$0.00239
Haiku 4.5	$0.00005	$0.00119

Measured 2mo ago against content hash a8e517407a2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triage-malware 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 2mo 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.

skills/triage-malware/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Malware Triage Skill

Perform initial analysis and context gathering for a suspected malicious file hash identified during an investigation or alert.

Inputs

FILE_HASH - MD5, SHA1, or SHA256 hash of the suspected file
CASE_ID - SOAR case ID for documentation
ALERT_GROUP_IDENTIFIERS - Alert group identifiers from the case
(Optional) TIME_FRAME_HOURS - Lookback period (default: 72)

Workflow

Step 1: Get Case Context

secops-soar.get_case_full_details(case_id=CASE_ID)

Step 2: GTI File Report

gti-mcp.get_file_report(hash=FILE_HASH)

Record:

Detection ratio (e.g., 45/70 engines)
Malware family classification
First/last seen dates
Associated threat actors or campaigns

Step 3: GTI Behavior Summary

gti-mcp.get_file_behavior_summary(hash=FILE_HASH)

Extract behavioral indicators:

Network: Contacted IPs/domains → NETWORK_IOCs_GTI
File system: Dropped files, modified files
Registry: Modified keys
MITRE TTPs: Observed techniques from sandbox

Step 4: SIEM Execution Check

Search for file execution events:

secops-mcp.search_security_events(
    text='target.file.sha256 = "FILE_HASH" OR target.file.md5 = "FILE_HASH"',
    hours_back=TIME_FRAME_HOURS
)

Look for: PROCESS_LAUNCH, FILE_CREATION, FILE_MODIFICATION

Identify:

AFFECTED_HOSTS - Machines where file was seen
AFFECTED_USERS - Users who executed/accessed the file

Step 5: SIEM Network Activity

Search for network connections from processes with this hash:

secops-mcp.search_security_events(
    text='principal.process.file.sha256 = "FILE_HASH"',
    hours_back=TIME_FRAME_HOURS
)

Extract: NETWORK_IOCs_SIEM (contacted IPs/domains)

Step 6: Enrich Network IOCs

Combine NETWORK_IOCs_GTI + NETWORK_IOCs_SIEM → ALL_NETWORK_IOCs

For each network IOC, use /enrich-ioc:

Check GTI reputation
Check SIEM presence
Check IOC match status

Step 7: Check Related Cases

Use /find-relevant-case with:

SEARCH_TERMS = AFFECTED_HOSTS + AFFECTED_USERS + ALL_NETWORK_IOCs

Read the full file on GitHub · 165 lines

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.

2mo ago First seen · 165 lines · 48 tokens per session scan A a8e517407a2c

Subscribe to this mod's changes

triage-malware is a skill published in the GitHub repository dandye/ai-runbooks (132 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,193 once invoked, about $0.0002 per session on Opus 5.5. 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.