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 llm-redteamgit 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/llm-redteam)<a href="https://agentmods.dev/skills/purpleailab/decepticon/llm-redteam"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/llm-redteam/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/llm-redteam"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/llm-redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01515 |
| Opus 5 | $0.00029 | $0.00758 |
| Sonnet 5 | $0.00012 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
llm-redteam-overview 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 10d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Red Team Skill Catalog — AATMF v3
This is the routing skill for AI/LLM red-team work. The 15 sub-skills below cover every tactic in the AI/ML Adversarial Tactics, Techniques & Mitigations Framework (AATMF v3). Load the specific sub-skill that matches the attacker objective.
Tactic Map
| Tactic | Sub-Skill | Covers | Load Path |
|---|---|---|---|
| T01 | prompt-injection | Direct + indirect prompt injection, ASCII smuggling, payload-in-image, prompt leaking | load_skill("/skills/plugins/llm-redteam/t01-prompt-injection/SKILL.md") |
| T02 | linguistic-evasion | Translation/transliteration bypass, base64/leetspeak/emoji encoding, low-resource-language jailbreak, multi-lingual context split | load_skill("/skills/plugins/llm-redteam/t02-linguistic-evasion/SKILL.md") |
| T03 | reasoning-exploit | CoT / ReAct hijack, math/logic distractor, role-play escalation, hypothetical / counterfactual framing | load_skill("/skills/plugins/llm-redteam/t03-reasoning-exploit/SKILL.md") |
| T04 | memory-manipulation | Long-context overflow, conversation rewrite, sliding-window poisoning, "previous turn" forgery | load_skill("/skills/plugins/llm-redteam/t04-memory-manipulation/SKILL.md") |
| T05 | api-exploitation | Function-calling abuse, tool-schema confusion, parameter pollution, response-format coercion | load_skill("/skills/plugins/llm-redteam/t05-api-exploitation/SKILL.md") |
| T06 | training-poisoning | Backdoor trigger injection, label flip, RLHF reward hacking, fine-tune dataset contamination | load_skill("/skills/plugins/llm-redteam/t06-training-poisoning/SKILL.md") |
| T07 | output-exfil | Data-leak via reflection, side-channel via length/timing, watermark stripping, token-by-token exfil | load_skill("/skills/plugins/llm-redteam/t07-output-exfil/SKILL.md") |
| T08 | deception | Confident-hallucination weaponization, persona impersonation, source spoofing, "as the system says" framings | load_skill("/skills/plugins/llm-redteam/t08-deception/SKILL.md") |
| T09 | multimodal | Image/audio prompt injection, OCR-payload, steganographic prompts, adversarial perturbations | load_skill("/skills/plugins/llm-redteam/t09-multimodal/SKILL.md") |
| T10 | confidentiality-breach | System-prompt extraction, weight inference, training-data extraction, PII echo | load_skill("/skills/plugins/llm-redteam/t10-confidentiality-breach/SKILL.md") |
| T11 | agentic-exploit | Tool-chain hijack, autonomous-loop poisoning, plan-injection, sub-agent confusion | load_skill("/skills/plugins/llm-redteam/t11-agentic-exploit/SKILL.md") |
| T12 | rag-poisoning | RAG index injection, document smuggling, embedding-collision, retrieval-rank gaming | load_skill("/skills/plugins/llm-redteam/t12-rag-poisoning/SKILL.md") |
| T13 | supply-chain | Model registry tampering, dependency confusion (HF Hub, Ollama, MCP), serialization payload abuse | load_skill("/skills/plugins/llm-redteam/t13-supply-chain/SKILL.md") |
| T14 | infra-warfare | GPU resource abuse, billing-amplification, rate-limit DoS, cold-start abuse, region failover poisoning | load_skill("/skills/plugins/llm-redteam/t14-infra-warfare/SKILL.md") |
| T15 | human-ai-coupling | Operator manipulation via AI output, social engineering uplift, dark-pattern UX exploiting AI trust | load_skill("/skills/plugins/llm-redteam/t15-human-ai-coupling/SKILL.md") |
What ships with it
15 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.
- t01-prompt-injection/SKILL.md 4.0 KB
- t02-linguistic-evasion/SKILL.md 3.9 KB
- t03-reasoning-exploit/SKILL.md 3.5 KB
- t04-memory-manipulation/SKILL.md 3.9 KB
- t05-api-exploitation/SKILL.md 4.3 KB
- t06-training-poisoning/SKILL.md 3.3 KB
- t07-output-exfil/SKILL.md 4.0 KB
- t08-deception/SKILL.md 3.7 KB
- t09-multimodal/SKILL.md 4.0 KB
- t10-confidentiality-breach/SKILL.md 4.6 KB
- t11-agentic-exploit/SKILL.md 4.2 KB
- t12-rag-poisoning/SKILL.md 4.0 KB
- t13-supply-chain/SKILL.md 3.9 KB
- t14-infra-warfare/SKILL.md 3.4 KB
- t15-human-ai-coupling/SKILL.md 4.2 KB
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.
- 10d ago First seen · 69 lines · 58 tokens per session scan A ee8a3e1ff39a
llm-redteam-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,515 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
ai-hacker
Use when aI and LLM security testing — prompt injection, model manipulation, data exfiltration via AI. Use when testing AI-powered applications, finding prompt injection vulnerabilities, or assessing LLM-integrated systems.
resources
Prompt Guide LLM Settings: https://www.promptingguide.ai/introduction/settings Prompt Design: https://www.promptingguide.ai/introduction/elements.
omh-llm-app-dev
This is a Hermes-native llm-app-dev workflow skill.
omh-model-setup
This is a Hermes-native model-setup workflow skill.
model-onboarding
Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both lanes, price from documented list only, gate machine config on a served route, prove with the gates, close with a benchmark pair. Use when a…
baoyu-skill
A Chinese-language approach to explaining AI tools and writing prompts—instructions that tell an AI what you want. It emphasizes step-by-step teaching, hands-on testing, plain-language technical explanations, and organized knowledge sharing.