Show Notes
In this episode of BHIS Presents: AI Security Ops, the team tackles one of the biggest sources of confusion in modern AI: What’s the difference between prompts, skills, tools, memory, and sub-agents? These terms are everywhere in discussions about agentic AI. They’re often used interchangeably—but they describe very different capabilities. More importantly, each one introduces its own unique security risks. If you’re building, deploying, or securing AI agents, understanding this vocabulary isn’t just helpful. It’s essential. Because every new capability an agent gains is also a new attack surface. We break down each core building block of agentic systems, explain what it actually does, and discuss how attackers can abuse it—from prompt injection and memory poisoning to supply-chain attacks and excessive tool permissions. We dig into: - The difference between prompts, skills, tools, memory, and sub-agents - Why prompts define behavior but don’t create lasting capability - How skills package reusable expertise without granting new permissions - Why tools are what allow AI agents to take real-world actions - The security risks of giving agents excessive privileges - How prompt injection remains the biggest threat facing AI agents today - Why memory transforms a one-time attack into a persistent compromise - How memory poisoning can influence future conversations - Why sub-agents improve scalability while creating new trust boundaries - The dangers of delegation, confused deputies, and poisoned summaries - Why every new capability increases an agent’s attack surface - How applying least privilege dramatically reduces AI security risk This episode explores one of the most important mental models in agentic AI: think of an AI agent like a new employee. The prompt is the job description. Skills are the documented procedures. Tools are the systems they’re allowed to access. Memory is their notebook. Sub-agents are the coworkers they delegate work to. Every one of those components makes an agent more capable—and every one creates new opportunities for something to go wrong. The takeaway: don’t evaluate an AI agent by how intelligent it is. Evaluate what it can access, what it can change, what it remembers, and who it trusts. — Chapters 0:00 – Intro: Understanding Agentic AI Terminology 1:18 – Prompts: Instructions and Prompt Injection 3:18 – Skills: Reusable Knowledge and Supply Chain Risk 5:18 – Tools: Permissions, Actions, and Least Privilege 7:40 – Memory: Persistence and Memory Poisoning 10:08 – Sub-Agents: Delegation and Trust Chains 12:18 – Putting It All Together: Expanding Attack Surface 14:05 – Final Takeaways — Key Concepts & Topics Prompts - System prompts vs. user prompts - Temporary instructions - Prompt injection attacks - Trusted vs. untrusted inputs Skills - Reusable task expertise - On-demand procedural knowledge - Context efficiency - Supply-chain trust Tools - External capabilities - Email, web search, databases, and code execution - Permission boundaries - Least privilege Memory - Persistent context - Long-term personalization - Memory poisoning - Privacy and data protection Sub-Agents - Task delegation - Isolated context windows - Confused deputy attacks - Trust boundaries Agent Security - Expanding attack surface - Capability versus risk - Secure agent design - Defense-in-depth for AI systems Learn more about Black Hills Information Security: https://www.blackhillsinfosec.com/ Check out Antisyphon Training: https://www.antisyphontraining.com/ #AISecurity #CyberSecurity #LLMSecurity #ArtificialIntelligence #AgenticAI #AIAgents #PromptInjection #InfoSec #BHIS #Antisyphon (00:00) - Intro: Understanding Agentic AI Terminology
(01:28) - Prompts: Instructions and Prompt Injection
(07:00) - Skills: Reusable Knowledge and Supply Chain Risk
(11:55) - Tools: Permissions, Actions, and Least Privilege
(14:50) - Memory: Persistence and Memory Poisoning
(22:54) - Sub-Agents: Delegation and Trust Chains
(26:52) - Putting I
More from AI Security Ops
In this episode of BHIS Presents: AI Security Ops, the team digs into some of the strangest recent examples of AI behaving badly. An AI agent finds a way around its sandbox using DNS. Malware asks four different AI models what it should do next. Attackers overwrite an AI agent’s “soul.” And a placeholder domain buried across GitHub becomes an unexpected security risk. Funny stories? Absolutely. But underneath them are some very familiar security problems. We dig into: - An OpenAI agent finding an unexpected path out through DNS - Whether a 2.5-hour response is fast enough in the age of AI - CLOSEDQUORUM malware using multiple AI models to make decisions - Why outbound AI API traffic could become a useful detection signal - The Carbonado botnet rewriting an agent’s SOUL.md instructions - The risks of exposed Docker daemons - How an unreserved placeholder domain can become an attack vector - Why AI agents make old security mistakes more consequential The takeaway: none of these techniques are particularly new. DNS tunneling, exposed services, compromised configuration files, and untrusted domains have existed for years. AI just gives attackers — and occasionally AI agents themselves — new ways to find and exploit those boring gaps at greater speed and scale. 2026-09-29-News (1).docx (00:00) - Intro: AI Behaving Badly
In this episode of BHIS Presents: AI Security Ops, the team continues its breakdown of the OWASP Agentic Skills Top 10, covering risks six through ten. Agentic skills may look like simple instructions, but they operate inside AI systems with access to tools, files, networks, and other resources. So what happens when those skills aren’t isolated, verified, monitored, or governed? We dig into: - AST06: Weak Isolation - AST07: Update Drift - AST08: Poor Scanning - AST09: No Governance - AST10: Cross-Platform Reuse - Why sandboxing the agent isn’t the same as isolating individual skills - The security tradeoffs between automatic updates and outdated skills - Why traditional scanners struggle with malicious instructions written in plain English - The importance of maintaining an inventory of agentic skills - How security controls can disappear when skills move between platforms The takeaway: securing agentic skills requires more than checking them once before installation. Organizations need visibility into what skills are running, what they can access, how they change, and whether their security controls survive across environments. OWASPAgenticSkils-Part2.docx This is Part 2 of our look at the OWASP Agentic Skills Top 10, covering AST06 through AST10. Part 1 can be found here #AISecurity #CyberSecurity #AgenticAI #AIAgents #OWASP #LLMSecurity #InfoSec #BHIS #Antisyphon
In this episode of BHIS Presents: AI Security Ops, the team tackles a big question: Could AI actually take over the internet? Recent warnings from AI industry leaders have raised concerns about autonomous agent swarms escaping containment, compromising systems, and operating at a scale humans may struggle to match. But what would “taking over the internet” actually require? The team looks at the problem from a hacker’s perspective — examining compute requirements, persistence, botnets, vulnerable infrastructure, the recent Hugging Face incident, and the difference between AI acting autonomously and humans using AI to accelerate attacks. We dig into: - Whether an autonomous AI swarm could realistically operate at internet scale - What the Hugging Face incident actually tells us about agentic security - The compute and infrastructure required to sustain a rogue agent swarm - How botnets and compromised systems could change the equation - Why existing vulnerabilities may be a bigger concern than hypothetical AI takeover scenarios - Whether slowing frontier AI development actually addresses the cybersecurity problem - The difference between AI exhibiting dangerous behavior and AI having intent - Why defenders need to focus on their real-world attack surface today The takeaway: AI is dramatically increasing the speed and scale of cybersecurity operations, but powerful models still operate inside systems designed, deployed, and connected by people. The immediate security question may be less “Will AI take over?” and more “What are we giving AI access to?”
In this episode of BHIS Presents: AI Security Ops, the team breaks down the first five risks in the OWASP Agentic Skills Top 10 (Part 1). Agentic skills can give AI systems reusable instructions, workflows, and capabilities — but they also introduce a new attack surface. A skill may look like a simple markdown file, yet the agent following those instructions could have access to your filesystem, credentials, network, shell, or other sensitive resources. We dig into: - AST01: Malicious Skills - AST02: Supply Chain Compromise - AST03: Overprivileged Skills - AST04: Insecure Metadata - AST05: Untrusted External Instructions - Why skills should be treated more like software than configuration - How excessive permissions increase an agent’s blast radius - Why external content creates indirect prompt injection risks - How isolation, least privilege, and trusted sources can reduce risk The takeaway: “just markdown” isn’t necessarily harmless when an AI agent can act on what it reads. This is Part 1 of our look at the OWASP Agentic Skills Top 10, covering AST01 through AST05. — Learn more about Black Hills Information Security: https://www.blackhillsinfosec.com/ Check out Antisyphon Training: https://www.antisyphontraining.com/ (00:00) - Intro: OWASP Agentic Skills Top 10, Part 1
Agentic skills can make AI agents more capable and consistent—but they can also introduce serious security risks. This episode explains how skills work, why malicious skills rank as a leading OWASP concern, and how seemingly harmless Markdown instructions can enable credential theft, remote payload delivery, and manipulated recommendations. Real-world examples illustrate how malicious skills can evade scanners and exploit trusted marketplaces. The episode concludes with practical safeguards, including reviewing skill files, watching for external instructions and prompt injection, pinning versions, limiting permissions, and running agents inside isolated environments. Links: OWASP Agentic Skills Top 10 Malicious AI Agent Skill Bypasses Security Scans and Seizes Full Control of Over 26,000 Agents (00:00) - Agentic Skills and the OWASP Top 10