--- title: Introducing Adversary Intelligence: LLM Tradecraft description: SpecterOps has launched a new on-demand training course, Adversary Intelligence: LLM Tradecraft, built in partnership with OpenAI. The ten-module course... canonical: https://daily.dev/posts/introducing-adversary-intelligence-llm-tradecraft-zjzrtpg4k twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Adversary Intelligence: LLM Tradecraft | daily.dev og:description: SpecterOps has launched a new on-demand training course, Adversary Intelligence: LLM Tradecraft, built in partnership with OpenAI. The ten-module course... og:url: https://daily.dev/posts/introducing-adversary-intelligence-llm-tradecraft-zjzrtpg4k og:image: https://api.daily.dev/og/posts/zjzrTpG4k.png og:image:alt: Introducing Adversary Intelligence: LLM Tradecraft og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing Adversary Intelligence: LLM Tradecraft **[SpecterOps](https://daily.dev/sources/specterops)** · 7 min read · 0 upvotes · 0 comments ## Summary SpecterOps has launched a new on-demand training course, Adversary Intelligence: LLM Tradecraft, built in partnership with OpenAI. The ten-module course teaches security practitioners how modern LLMs and agentic systems work, covering ML fundamentals, prompting, agent architectures, MCP security, threat modeling for LLM applications, jailbreaks and prompt injection defenses, and using Codex for tasks like incident investigation and reverse engineering. Each module includes hosted hands-on labs. Enrollment opens with the first cohort starting October 15, offering 30 days of access plus a ChatGPT Pro subscription from OpenAI. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What topics does a course on securing LLMs and AI agents for security practitioners typically cover? A comprehensive LLM security curriculum can span machine learning foundations, transformer mechanics, prompting techniques, agent architectures, Model Context Protocol (MCP) risks, evaluation and observability, LLM threat modeling, jailbreaks and prompt injection defenses, and using coding agents like Codex for tasks such as incident investigation, reverse engineering, and threat modeling. _Developers building or securing agentic systems can follow ongoing MCP and prompt-injection coverage on daily.dev._ ### What security risks does the Model Context Protocol (MCP) introduce for AI agents? MCP connects clients to tools and data sources, and its risks include local and remote server vulnerabilities, tool-description injection, dynamic definition changes, and tool hijacking, alongside familiar API issues like missing authorization, injection attacks, confused-deputy behavior, and server-side request forgery (SSRF). These risks arise because tool definitions and results flow directly into the model's context. _Teams adopting MCP for agent tooling can track emerging attack patterns and defenses on daily.dev._ ## Similar posts on daily.dev - [Demystifying Agent Tradecraft: Introducing SpecterOps Skills](https://daily.dev/posts/demystifying-agent-tradecraft-introducing-specterops-skills-fkdmgshdy) · SpecterOps · 1 upvotes · 0 comments - [LLM-Generated Mythic Agents Enable Disposable Red-Team Tooling](https://daily.dev/posts/llm-generated-mythic-agents-enable-disposable-red-team-tooling-bx5ghnvyo) · Security Boulevard · 0 upvotes · 0 comments - [The Complete Guide to LLM Security: Risks, Best Practices, and Solutions](https://daily.dev/posts/the-complete-guide-to-llm-security-risks-best-practices-and-solutions-8ug63q2np) · Orca Security Blog · 0 upvotes · 0 comments - [From Noise to Insight: How LLMs Are Transforming Threat Intelligence Analysis](https://daily.dev/posts/from-noise-to-insight-how-llms-are-transforming-threat-intelligence-analysis-uajq44mzh) · Flipkart Tech · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#prompt-injection](https://daily.dev/tags/prompt-injection), [#openai-codex](https://daily.dev/tags/openai-codex) [View this post on daily.dev](https://daily.dev/posts/introducing-adversary-intelligence-llm-tradecraft-zjzrtpg4k) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Adversary Intelligence: LLM Tradecraft","url":"https://daily.dev/posts/introducing-adversary-intelligence-llm-tradecraft-zjzrtpg4k","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-adversary-intelligence-llm-tradecraft-zjzrtpg4k"},"datePublished":"2026-09-30T11:31:40.969Z","dateModified":"2026-09-30T11:32:03.157Z","description":"SpecterOps has launched a new on-demand training course, Adversary Intelligence: LLM Tradecraft, built in partnership with OpenAI. The ten-module course...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/efd4c439dd58189b831017fe344af03d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/efd4c439dd58189b831017fe344af03d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"SpecterOps","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"SpecterOps","logo":"https://media.daily.dev/image/upload/s--lR36Z4gn--/f_auto,q_auto/v1787487384/logos/specterops?_a=BAMAMicg0","url":"https://daily.dev/sources/specterops"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-adversary-intelligence-llm-tradecraft-zjzrtpg4k","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,mcp,prompt-injection,openai-codex","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"SpecterOps","item":"https://daily.dev/sources/specterops"},{"@type":"ListItem","position":3,"name":"Introducing Adversary Intelligence: LLM Tradecraft"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-adversary-intelligence-llm-tradecraft-zjzrtpg4k#faq","mainEntity":[{"@type":"Question","name":"What topics does a course on securing LLMs and AI agents for security practitioners typically cover?","acceptedAnswer":{"@type":"Answer","text":"A comprehensive LLM security curriculum can span machine learning foundations, transformer mechanics, prompting techniques, agent architectures, Model Context Protocol (MCP) risks, evaluation and observability, LLM threat modeling, jailbreaks and prompt injection defenses, and using coding agents like Codex for tasks such as incident investigation, reverse engineering, and threat modeling. Developers building or securing agentic systems can follow ongoing MCP and prompt-injection coverage on daily.dev."}},{"@type":"Question","name":"What security risks does the Model Context Protocol (MCP) introduce for AI agents?","acceptedAnswer":{"@type":"Answer","text":"MCP connects clients to tools and data sources, and its risks include local and remote server vulnerabilities, tool-description injection, dynamic definition changes, and tool hijacking, alongside familiar API issues like missing authorization, injection attacks, confused-deputy behavior, and server-side request forgery (SSRF). These risks arise because tool definitions and results flow directly into the model's context. Teams adopting MCP for agent tooling can track emerging attack patterns and defenses on daily.dev."}}]} ```