ti-ioc-extraction

ti-ioc-extraction is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 75 tokens per session (4,886 once invoked), scanned A, original, Apache-2.0.

A guide to extracting indicators of compromise, such as file hashes, IP addresses, domains, URLs, email addresses, and CVE identifiers, from unstructured text.

In plain words
What is it for?
It is for extracting, normalizing, refanging, deduplicating, and exporting indicators to formats such as STIX, TAXII, MISP, YARA rules, and blocklists.
Why use it?
It turns threat reports, logs, and pasted text into cleaned and deduplicated data that security tools can use.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It is for extracting, normalizing, refanging, deduplicating, and exporting indicators to formats such as STIX, TAXII, MISP, YARA rules, and blocklists.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/ti-ioc-extraction
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,482 stars · on GitHub · decepticon.red

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 PurpleAILAB/Decepticon --skill ti-ioc-extraction
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code.

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 ti-ioc-extraction

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/ti-ioc-extraction/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/ti-ioc-extraction)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/ti-ioc-extraction"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ti-ioc-extraction/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 ti-ioc-extraction

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/ti-ioc-extraction"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ti-ioc-extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Supply Chain · line 191
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • high Supply Chain · line 204
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • medium Data Exfiltration · line 204
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 212
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.04886
Opus 5 $0.00037 $0.02443
Sonnet 5 $0.00015 $0.00977
Haiku 4.5 $0.00007 $0.00489

Measured 7d ago against content hash de6c43f1f52e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ti-ioc-extraction scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

result=$(curl -s "https://www.virustotal.com/api/v3/files/$hash" \
packages/decepticon/decepticon/skills/standard/analyst/ti-ioc-extraction/SKILL.md · 439 lines

How it starts

The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IOC Extraction from Unstructured Text

Extract Indicators of Compromise from threat intelligence reports, incident logs, paste dumps, and raw text. Normalize, deduplicate, and format for downstream consumption (MISP, STIX/TAXII feeds, YARA rules, blocklists).

Quick Reference

# Install tools
pip install ioc-finder ioc_fanger stix2 pymisp

# One-shot extraction from a report file
python3 -c "
from ioc_finder import find_iocs
text = open('/workspace/report.txt').read()
iocs = find_iocs(text)
for k,v in iocs.items():
    if v: print(f'{k}: {v}')
"

# Refang a defanged IOC list
python3 -c "
from ioc_fanger import fang
text = open('/workspace/defanged_iocs.txt').read()
print(fang(text))
" > /workspace/refanged_iocs.txt

# Quick regex extraction (no deps)
grep -oP '\b[0-9a-fA-F]{32}\b' /workspace/report.txt | sort -u > /workspace/md5_hashes.txt
grep -oP '\b[0-9a-fA-F]{64}\b' /workspace/report.txt | sort -u > /workspace/sha256_hashes.txt
grep -oP '\b(?:[0-9]{1,3}\.){3}[0-9]{1,3}\b' /workspace/report.txt | sort -u > /workspace/ips.txt

MITRE ATT&CK Mapping

Technique ID Relevance
Gather Victim Network Information T1590 Extracted IPs, domains, and URLs map victim-facing infrastructure
Gather Victim Host Information T1592 Extracted file hashes, registry keys, and file paths indicate host-level artifacts
Phishing T1566 Extracted email addresses and sender domains from phishing report IOCs
Indicator Removal T1070 Awareness of IOC types attackers attempt to obscure or rotate

1. Regex-Based IOC Extraction

When ioc-finder is unavailable or you need precise control, use these regex patterns:

# MD5 hashes (32 hex chars, standalone word boundary)
grep -oP '\b[0-9a-fA-F]{32}\b' /workspace/<REPORT> | sort -u > /workspace/iocs/md5.txt

# SHA1 hashes (40 hex chars)
grep -oP '\b[0-9a-fA-F]{40}\b' /workspace/<REPORT> | sort -u > /workspace/iocs/sha1.txt

# SHA256 hashes (64 hex chars)
grep -oP '\b[0-9a-fA-F]{64}\b' /workspace/<REPORT> | sort -u > /workspace/iocs/sha256.txt

# IPv4 addresses
grep -oP '\b(?:(?:25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(?:25[0-5]|2[0-4]\d|[01]?\d\d?)\b' \
  /workspace/<REPORT> | sort -u > /workspace/iocs/ipv4.txt

# IPv6 addresses (simplified — catches common forms)
grep -oiP '(?:[0-9a-f]{1,4}:){7}[0-9a-f]{1,4}|(?:[0-9a-f]{1,4}:){1,7}:|::(?:[0-9a-f]{1,4}:){0,5}[0-9a-f]{1,4}' \
  /workspace/<REPORT> | sort -u > /workspace/iocs/ipv6.txt

# Domain names (basic, excludes common FPs)
grep -oP '(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+(?:com|net|org|io|ru|cn|xyz|top|info|biz|cc|tk|ml|ga|cf|pw|buzz|su|onion)\b' \
  /workspace/<REPORT> | sort -u > /workspace/iocs/domains.txt

# URLs (http/https/ftp)
grep -oP 'https?://[^\s"<>\])+' /workspace/<REPORT> | sort -u > /workspace/iocs/urls.txt

# Email addresses
grep -oP '[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}' \
  /workspace/<REPORT> | sort -u > /workspace/iocs/emails.txt

# CVE identifiers
grep -oP 'CVE-\d{4}-\d{4,7}' /workspace/<REPORT> | sort -u > /workspace/iocs/cves.txt

# MITRE ATT&CK technique IDs
grep -oP 'T\d{4}(?:\.\d{3})?' /workspace/<REPORT> | sort -u > /workspace/iocs/mitre_ids.txt

Read the full file on GitHub · 439 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.

  1. 7d ago First seen · 439 lines · 75 tokens per session scan A de6c43f1f52e

Subscribe to this mod's changes

ti-ioc-extraction is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 75 tokens to every session and 4,886 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.