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 agentmods add skills/purpleailab/decepticon/misinformationnpx skills add PurpleAILAB/Decepticon --skill misinformationgit 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/misinformation)<a href="https://agentmods.dev/skills/purpleailab/decepticon/misinformation"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/misinformation.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.01500 |
| Opus 5 | $0.00024 | $0.00750 |
| Sonnet 5 | $0.00010 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
misinformation 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Misinformation and Overreliance (LLM09:2025)
LLMs are confident liars by default. The vuln class is not "models hallucinate" — that's a behaviour. The finding is "the product takes business-material action on unverified model output". The pattern appears whenever automation skips the human-review step that a static expert system would have required.
1. Recognition signals
- The product publishes model output directly to customers / partners / regulators (email, ticket reply, status page, generated contract).
- Agentic system commits code / merges PRs based on model judgement.
- Risk / fraud / KYC decisions are routed through an LLM with no documented override loop.
- "AI second opinion" feature on health / legal / financial advice.
- Code-generation tools auto-fix vulnerabilities and re-deploy.
- Compliance summaries / audit reports generated by LLM and signed off.
- Translation / localisation of safety-critical text without review.
2. Attack vectors
Manufactured uncertainty
Prompt the model into an edge case where any answer is wrong (vague legal hypothetical, contradictory inputs). The downstream sink commits to the answer regardless.
Package hallucination → typosquat
Code-gen LLM hallucinates a dependency name. Attacker registers the hallucinated package on PyPI / npm. Build pipelines that re-install the hallucinated package now run attacker code. (Known good vector for years; still works.)
Fabricated citation in a generated report
The model invents authoritative-sounding source URLs or case references. A compliance / legal team adopts the report and ships the falsehood downstream.
Bias amplification on auto-decision endpoints
The model rates resumes / loan applications / fraud signals. The training distribution biases the decision; the product applies it at scale.
Confidence laundering
The product strips the model's uncertainty markers ("I think...", "It's possible that...") and presents the residual sentence as fact.
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.
- yesterday First seen · 151 lines · 49 tokens per session scan A fb70970ba062
misinformation is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,445 stars, last pushed 5d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,500 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
add-model
Add a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system.
langchain-patterns
Use when langChain/LangGraph patterns — chains, agents, tools, memory, retrieval, graph workflows. Use when working with langchain patterns.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
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.
langchain-architecture
Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
crawl4ai
Complete toolkit for web crawling and data extraction using Crawl4AI. This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for…