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
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 skills add PurpleAILAB/Decepticon --skill dark-caracalgit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote 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/dark-caracal)<a href="https://agentmods.dev/skills/purpleailab/decepticon/dark-caracal"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dark-caracal/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/dark-caracal"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dark-caracal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Privilege Escalation · line 63 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high YARA Match · line 141 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Rogue Agent · line 143 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 144 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 161 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00051 | $0.05707 |
| Opus 5 | $0.00026 | $0.02854 |
| Sonnet 5 | $0.00010 | $0.01141 |
| Haiku 4.5 | $0.00005 | $0.00571 |
Grade A, and why
dark-caracal 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 11d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dark Caracal — Adversary Emulation Profile
Dark Caracal (MITRE ATT&CK G0070) is a cyber-espionage and surveillance group attributed to Lebanon's General Directorate of General Security (GDGS), operating since at least 2012. The group is best characterized by its mobile-first surveillance approach — deploying trojanized Android messaging apps (Pallas) to harvest SMS, call logs, contacts, photos, and real-time audio/video — combined with cross-platform desktop RATs (Bandook, CrossRAT) and the commercial spyware FinFisher. Dark Caracal relies on relatively simple social engineering — phishing via Facebook and WhatsApp, watering holes, and trojanized applications masquerading as popular software — rather than advanced zero-day exploitation. Despite this simplicity, the group has compromised thousands of victims across 20+ countries, exfiltrating hundreds of thousands of files and text messages. Evidence suggests the group may also operate as a cyber-mercenary / hack-for-hire entity, conducting campaigns on behalf of other governments (notably Kazakhstan in Operation Manul).
Attribution & motivation
- Sponsor / nation: Republic of Lebanon — General Directorate of General Security (GDGS), the country's primary intelligence agency. The 2018 EFF/Lookout investigation traced C2 infrastructure to a building adjacent to GDGS headquarters in Beirut, with test devices physically located in the same building.
- Motivation: Primarily espionage and surveillance — long-term intelligence collection against individuals (journalists, activists, dissidents, lawyers, military personnel) rather than organizations. Secondary motivation includes hack-for-hire / mercenary operations for foreign governments (Kazakhstan in Operation Manul).
- Attribution confidence: High. Backed by the joint EFF/Lookout 2018 investigation tracing infrastructure to GDGS premises, corroborated by shared infrastructure with Operation Manul (2016 EFF report), and consistent vendor reporting (Check Point, ESET, Positive Technologies, Cofense).
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.
- 11d ago First seen · 180 lines · 51 tokens per session scan A 87038e3eb499
dark-caracal is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 51 tokens to every session and 5,707 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 2026-08-30.
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.