Fable in Action: A Field Test
A hands-on field test of Fable on real cybersecurity work. What it nails, where it breaks and the safety line…
Category: Red Teaming LLMs
![[Local Lab]: Agentic Overdelegation](https://mamtaupadhyay.com/wp-content/uploads/2025/06/image-with-text-local-lab-agent-overdelegation-2.png)
[Local Lab]: Agentic Overdelegation
Demo to explore how AI agents can be manipulated to misuse tools
MCP Chains That Use Web Scraping
What would you target first in a prompt pipeline that scrapes the web?
Shadow Agents: Red Teaming Multi-Agent LLM Coordination
Shadow agents are stealth behaviors that emerge in multi-agent LLM systems
LLM Inception with Memory Retention & Behavioral Conditioning
This content is just for subscribers. Join the community (it’s free!) below to unlock it.
Hijacking Your AI: When Web Attacks & Prompt Injection Collide
What happens when classic web exploits meet modern AI?
ASCII Smuggling in LLMs
How attackers use invisible characters to bypass LLM filters and inject prompts without a trace
