Skip to content

Back to the catalog

becomingahacker.orgarticle

AI Agents for Cybersecurity: A Guided Tour of a Repository with Tons of Resources and Examples

Omar Santos walks through his eight-part AI-agents-for-cybersecurity repository: LLM building blocks (LangChain, RAG), then security agents with LangGraph, CrewAI, DeepAgents and MCP servers (nmap, CISA KEV, Shodan), a hardening guide for six agentic frameworks, token-cost control for agents, and a spec for a supervisor-led, human-gated security-assessment harness. It covers concrete design lessons such as least-privilege subagents, staged response actions, single-use approvals bound to exact actions, kill switches, and mapping controls to the OWASP Top 10 for Agentic Applications. Also notes Project CodeGuard rules shipped for AI coding assistants.

TL;DR Guided tour of Omar Santos's AI-agents-for-cybersecurity repo: building security agents, MCP servers, framework hardening, token costs, and a human-gated assessment harness spec.
Open original ↗

Organisations named here

  • Artificial Analysis Cyber Index
  • CoSAI
  • MITRE ATT&CK
  • Omar Santos

Technologies named here

  • AI-agents-for-cybersecurity repository
  • OpenClaw
  • OpenHands
  • LangChain 1.x / LangGraph
  • CrewAI
  • Hermes
  • deepagents
  • MCP stacks with 10,000–25,000 schema tokens per call
  • Exploit-DB search
  • subfinder and nuclei
  • CISA Known Exploited Vulnerabilities Catalog
  • NVD API
  • Chroma
  • Ollama
  • Part 6 frameworks
  • Artificial Analysis Cyber Index
  • MITRE ATT&CK
  • PentestGPT, CyberSecEval 4
  • LangChain
  • Model Context Protocol
  • Python
  • Nmap
  • Shodan
  • CISA KEV
  • Project CodeGuard
  • OWASP Top 10 for Agentic Applications
  • Foundry Security Spec

Techniques named here

  • Indirect prompt injection
  • Skill and plugin supply-chain attacks
  • Persistent Memory Poisoning
  • Command injection via crafted hostname
  • Approval fatigue with fail-open defaults
  • Exposed agent control surfaces
  • Compaction summaries laundering prompt injection
  • Shared cache leakage across tenants
  • Agentic RAG
  • Context quarantine via subagents
  • Embedding clustering of CVEs
  • Simulated attack-surface management
  • Denial of wallet

Related in AI Security