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.
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/PurpleAILAB/Decepticonnpx agentmods add skills/purpleailab/decepticon/ti-yara-huntingWrote 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/purpleailab/decepticon/ti-yara-hunting)<a href="https://agentmods.dev/skills/purpleailab/decepticon/ti-yara-hunting"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ti-yara-hunting/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/purpleailab/decepticon/ti-yara-hunting"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ti-yara-hunting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 294 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 294 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 330 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 346 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.
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 | $0.00058 | $0.05281 |
| Opus 5 | $0.00029 | $0.02641 |
| Sonnet 5 | $0.00012 | $0.01056 |
| Haiku 4.5 | $0.00006 | $0.00528 |
Grade A, and why
ti-yara-hunting 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "https://www.virustotal.com/api/v3/intelligence/retrohunt_jobs" \ How it starts
The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YARA Hunting
Write YARA rules from malware samples, behavioral observations, and threat intelligence reports. Deploy rules for retrohunting across VirusTotal (500M+ files) and ANY.RUN (2TB malware corpus) to discover campaign variants, earlier versions, and related infrastructure.
Quick Reference
# Install YARA
apt-get install -y yara || pip install yara-python
# Install YARA-X (Rust rewrite — faster, stricter)
cargo install yara-x
# Install yarGen for automated rule generation
git clone https://github.com/Neo23x0/yarGen.git /opt/yarGen
cd /opt/yarGen && pip install -r requirements.txt
python3 yarGen.py --update # Download goodware string DB (first run only)
# Scan a file with a rule
yara /workspace/rules/suspect.yar /workspace/samples/
# Compile rules for faster scanning
yarac /workspace/rules/*.yar /workspace/rules/compiled.yarc
yara /workspace/rules/compiled.yarc /workspace/samples/
# Validate rule syntax (YARA-X — stricter parser)
yr check /workspace/rules/suspect.yar
MITRE ATT&CK Mapping
| Technique | ID | Relevance |
|---|---|---|
| Obtain Capabilities: Exploits | T1588.005 | YARA identifies exploit tools/payloads in attacker arsenals |
| Develop Capabilities: Malware | T1587.001 | Rules detect custom malware based on unique strings/structures |
| Gather Victim Host Information: Software | T1592.002 | YARA scans reveal installed malware on victim hosts |
| Indicator Removal on Host | T1070 | Retrohunting finds samples attackers attempted to erase |
1. YARA Rule Syntax
Minimal Rule Structure
rule Malware_FamilyName_Variant {
meta:
author = "Decepticon TI"
date = "2025-01-01"
description = "Detects FamilyName variant based on unique strings"
hash = "e3b0c44298fc1c149afbf4c8996fb924..."
reference = "https://report-url"
tlp = "WHITE"
strings:
$s1 = "unique_string_from_sample" ascii wide
$s2 = { 4D 5A 90 00 03 00 00 00 } // MZ header + specific bytes
$s3 = /https?:\/\/[a-z0-9\-\.]+\/gate\.php/ nocase
condition:
uint16(0) == 0x5A4D and // PE file check
filesize < 5MB and
2 of ($s*)
}
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 · 444 lines · 58 tokens per session scan A bfb7df45d154
ti-yara-hunting is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 58 tokens to every session and 5,281 once invoked, about $0.0003 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.
Other skills, from other repositories
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
idea-generation
Stock screening and idea generation: quantitative screens, thematic analysis, shortlist.
secretary
Workspace and research management — dispatch analyses, monitor running agents, manage workspaces and threads.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
analyzing-windows-prefetch-with-python
Use when parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns. Use when working with analyzing windows prefetch with python.