| Bonus Resources.txt | 102.4 B | ||
| Get Bonus Downloads Here.url | 204.8 B | ||
| README.md | 5.4 KB | ||
| docker-compose.yml | 2.1 KB | ||
| requirements.txt | 819.2 B | ||
| taskpilot | |||
| README.md | 2.2 KB | ||
| __init__.py | 1.1 KB | ||
| agent.py | 3.9 KB | ||
| cli.py | 1 KB | ||
| config.py | 3.6 KB | ||
| db.py | 2.1 KB | ||
| defenses.py | 2.7 KB | ||
| tools | |||
| build-showcase.py | 5.3 KB | ||
| build-student-zip.sh | 1 KB | ||
| record-showcase.py | 5.6 KB | ||
| termcast.py | 5.5 KB | ||
| webapp | |||
| Dockerfile | 921.6 B | ||
| README.md | 4.6 KB | ||
| index.html | 15.8 KB | ||
| resources | |||
| agent-incident-response-runbook.md | 2.1 KB | ||
| agent-threat-model-template.md | 1.7 KB | ||
| audit-log-schema.json | 1.3 KB | ||
| framework-mappings.md | 2.7 KB | ||
| least-privilege-checklist.md | 1.7 KB | ||
| secure-tool-design-checklist.md | 1.8 KB | ||
| setup | |||
| 2 - Prompt Injection in Agent Loops | |||
| 10. RAG & Memory Poisoning — Persisting the Payload.mp4 | 15.3 MB | ||
| 11. Defenses I — Spotlighting, Delimiting & Dual-LLM Patterns.mp4 | 14.4 MB | ||
| 12. Defenses II — Output Handling & Injection Detection.mp4 | 24.7 MB | ||
| 13. Lab 2 — Indirect Prompt Injection & Defenses.mp4 | 36.8 MB | ||
| 2. Section 2 Quiz — Prompt Injection in Agent Loops.html | 23.3 KB | ||
| 3 - Tool-Calling Vulnerabilities | |||
| 14. Secure Tool Design — The Tool Is Your Trust Boundary.mp4 | 15.2 MB | ||
| 15. Argument & Command Injection in Tools.mp4 | 13.2 MB | ||
| 16. SSRF, Path Traversal & the Fetch and File Tools.mp4 | 16.5 MB | ||
| 17. MCP Server Security — Schemas, Descriptions & Trust.mp4 | 17.1 MB | ||
| 18. Hardening TaskPilot's Tools.mp4 | 14.3 MB | ||
| 19. Lab 3 — Tool Exploitation → Hardening.mp4 | 32.5 MB | ||
| 3. Section 3 Quiz — Tool-Calling Vulnerabilities.html | 22.8 KB | ||
| 4 - Excessive Agency & Least Privilege | |||
| 20. The Three Excesses — Functionality, Permissions, Autonomy.mp4 | 20 MB | ||
| 21. Least Privilege for Agents — Capability Scoping.mp4 | 12 MB | ||
| 22. Building a Permission Broker & MCP Scopes.mp4 | 13.6 MB | ||
| 23. Allow Deny & Approval Patterns the Claude Way.mp4 | 13.2 MB | ||
| 24. Lab 4 — Least Privilege & Permission Broker.mp4 | 36.1 MB | ||
| 4. Section 4 Quiz — Excessive Agency & Least Privilege.html | 22.7 KB | ||
| 5 - Multi-Step Execution & Memory Security | |||
| 25. Plan & Goal Hijacking — Steering the Multi-Step Loop.mp4 | 15.4 MB | ||
| 26. Memory & State Poisoning Across Sessions.mp4 | 15.8 MB | ||
| 27. Loop, Recursion & Cost Abuse — Denial of Wallet.mp4 | 12.6 MB | ||
| 28. Execution Guards — Step Limits, Budgets & Checkpoints.mp4 | 13.2 MB | ||
| 29. Lab 5 — Execution & Memory Guards.mp4 | 15.6 MB | ||
| 5. Section 5 Quiz — Multi-Step Execution & Memory Security.html | 22.7 KB | ||
| 6 - Multi-Agent & Autonomous Systems | |||
| 30. Agent-to-Agent Injection — Trust Between Agents.mp4 | 13.3 MB | ||
| 31. The Confused Deputy & Malicious Delegation.mp4 | 12.7 MB | ||
| 32. Orchestration Risk in CrewAI & AutoGen.mp4 | 12.7 MB | ||
| 33. Human-in-the-Loop Gates for Autonomy.mp4 | 14.7 MB | ||
| 34. Lab 6 — Multi-Agent Attack + Human-in-the-Loop.mp4 | 32.2 MB | ||
| 6. Section 6 Quiz — Multi-Agent & Autonomous Systems.html | 23.5 KB | ||
| 7 - Sandboxing, Isolation & Secure Execution | |||
| 35. Sandboxing Code Execution — Threat Model.mp4 | 14.3 MB | ||
| 36. Containers, Seccomp & Egress Control.mp4 | 14.8 MB | ||
| 37. Secrets, Credentials & the Blast Radius.mp4 | 21.8 MB | ||
| 38. Tool & MCP Supply Chain — Malicious Servers.mp4 | 14.3 MB | ||
| 39. Lab 7 — Sandbox the Code-Exec Tool.mp4 | 26.9 MB | ||
| 7. Section 7 Quiz — Sandboxing, Isolation & Secure Execution.html | 22.7 KB | ||
| 8 - Detection, Monitoring & Governance | |||
| 40. Tracing & Observability for Agents with OpenTelemetry.mp4 | 14.3 MB | ||
| 41. Runtime Guardrails — Input, Output & Action Filters.mp4 | 15.7 MB | ||
| 42. Automated Red-Teaming — Garak & PyRIT.mp4 | 14.1 MB | ||
| 43. Governance — NIST AI RMF, EU AI Act, ISO 42001.mp4 | 14.1 MB | ||
| 44. Incident Response & the Capstone Red-Team Report.mp4 | 15.6 MB | ||
| 45. Lab 8 (Capstone) — Defend & Report.mp4 | 28.9 MB | ||
| 8. Section 8 Quiz — Detection, Monitoring & Governance.html | 24.2 KB | ||
| 9. Final Exam — Securing Agentic AI (30 Q, 70% pass).html | 35.6 KB | ||
| Capstone — Produce a Client-Ready Agent Red-Team & Remediation Report.html | 6.1 KB | ||
| Write an Egress-Denied Sandbox Spec for an Agent's code_exec Tool.html | 4.4 KB | ||
| Threat-Model a Multi-Agent Crew's Trust Boundaries.html | 4.2 KB | ||
| Add Execution Guards and Memory Provenance to a Multi-Step Agent.html | 4.3 KB | ||
| Write a Least-Privilege Permission Policy for an Agent.html | 4.2 KB | ||
| Redesign an Agent Tool into a Secure Trust Boundary.html | 4.3 KB | ||
| 8. Direct Prompt Injection — Hijacking the Instruction Channel.mp4 | 23.9 MB | ||
| 9. Indirect Injection — When Tool Output Becomes a Command.mp4 | 12.6 MB | ||
| Build a 3-Layer Prompt-Injection Defense for an Agent Loop.html | 4.5 KB | ||
| setup-linux.sh | 1.1 KB | ||
| setup-macos.command | 1.2 KB | ||
| setup-windows.ps1 | 1.3 KB | ||
| setup-commands.md | 2.6 KB | ||
| server.py | 7.5 KB | ||
| tools.py | 7.9 KB | ||
| taskpilot-demo.html | 80.4 KB | ||
| ~Get Your Files Here ! | |||
| 1 - Foundations of Agent Security | |||
| 1. Section 1 Quiz — Foundations of Agent Security.html | 21.5 KB | ||
| 1. Welcome — Why Securing Agents Is a New Discipline.mp4 | 16.7 MB | ||
| 2. Anatomy of an Agent — The Perceive-Plan-Act Loop.mp4 | 15.5 MB | ||
| 3. The Agent Attack Surface — Where Trust Breaks.mp4 | 17.1 MB | ||
| 4. Threat Frameworks — OWASP, MITRE ATLAS, NIST AI RMF.mp4 | 15.8 MB | ||
| 5. Meet TaskPilot — Your Vulnerable Lab Agent.mp4 | 13.5 MB | ||
| 6. Set Up Your Lab Environment (macOS · Windows · Linux) (Description).html | 819.2 B | ||
| 6. Set Up Your Lab Environment (macOS · Windows · Linux).mp4 | 17.4 MB | ||
| 7. Lab 1 — Build & Map a Vulnerable Agent (TaskPilot).mp4 | 14.6 MB | ||
| Threat-Model an Agentic Workflow's Attack Surface.html | 3.8 KB | ||
| labs | |||
| L1-build-and-map | |||
| L2-prompt-injection | |||
| L3-tool-calling-vulns | |||
| L4-least-privilege | |||
| L5-execution-and-memory | |||
| L6-multi-agent | |||
| L7-sandboxing | |||
| L8-capstone | |||
| README.md | 2.4 KB | ||
| SOLUTION.md | 2.1 KB | ||
| demo.py | 1.9 KB | ||
| redteam-report.md | 2 KB | ||
| redteam.py | 5.5 KB | ||
| README.md | 2.2 KB | ||
| SOLUTION.md | 2 KB | ||
| demo.py | 1.7 KB | ||
| exploit.py | 2.4 KB | ||
| README.md | 2.4 KB | ||
| SOLUTION.md | 2 KB | ||
| demo.py | 1.8 KB | ||
| exploit.py | 2.8 KB | ||
| README.md | 2.2 KB | ||
| SOLUTION.md | 1.8 KB | ||
| demo.py | 1.6 KB | ||
| exploit.py | 2.7 KB | ||
| README.md | 2.2 KB | ||
| SOLUTION.md | 2.1 KB | ||
| demo.py | 1.6 KB | ||
| exploit.py | 2.2 KB | ||
| README.md | 2.2 KB | ||
| SOLUTION.md | 2.3 KB | ||
| demo.py | 2.1 KB | ||
| exploit.py | 2.2 KB | ||
| README.md | 2.6 KB | ||
| SOLUTION.md | 2.2 KB | ||
| demo.py | 2.1 KB | ||
| exploit.py | 2.8 KB | ||
| README.md | 3 KB | ||
| SOLUTION.md | 2.8 KB | ||
| demo.py | 2.9 KB | ||
| map_attack_surface.py | 1.7 KB |
Securing Agentic AI: Attack & Defend Autonomous Agents
https://WebToolTip.com
Published 7/2026
Created by Dr. Amar Massoud
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz, 2 Ch
Level: All Levels | Genre: eLearning | Language: English | Duration: 45 Lectures ( 3h 34m ) | Size: 795.8 MB
Hands-on agent security: prompt injection, tool abuse, least privilege, sandboxing & red-teaming with LangGraph/MCP
What you'll learn
⚡ Map the attack surface of any agentic workflow: tools, memory, plan loop, multi-agent edges
⚡ Exploit prompt injection (direct & indirect), tool/command/SSRF injection, memory poisoning
⚡ Hijack agent plans and trigger denial-of-wallet; defend with execution guards
⚡ Enforce least privilege with permission brokers, MCP scopes, and approval gates
⚡ Secure multi-agent systems (CrewAI/AutoGen) against agent-to-agent injection & confused-deputy
⚡ Sandbox code execution with containers + egress control; defend the tool/MCP supply chain
⚡ Instrument tracing, build runtime guardrails, and run automated red-teaming (Garak, PyRIT)
⚡ Write a governance-grade red-team report mapped to OWASP, ATLAS, NIST, EU AI Act, ISO 42001
Requirements
❗ Python fluency; familiarity with OWASP-style security frameworks
❗ Sandbox code execution with containers + egress control; defend the tool/MCP supply chain
| torrent name | size | uploader | age | seed | leech |
|---|---|---|---|---|---|
| 2.4 GB | freecoursewb | 5 months | 19 | 0 | |
|
Udemy - Pentesting GenAI LLM models - Securing Large Language Models Posted by
freecoursewb in Other
|
1.6 GB | freecoursewb | 1 year | 0 | 1 |
| 336 MB | freecoursewb | 2 years | 13 | 15 | |
| 496.7 MB | freecoursewb | 2 years | 0 | 0 | |
| 405.2 MB | freecoursewb | 2 years | 0 | 0 |
All Comments