How We Red-Teamed Our Own AI Agent: Lessons from Operation Pale Fire
Josiah Peedikayil, HS
BSidesSF 2026 · Day 2 · AMC Theatre 14
This talk, "How We Red-Teamed Our Own AI Agent: Lessons from Operation Pale Fire," presented by Josiah Peedikayil from Block's offensive security team, details a proactive **red team operation** targeting Block's internal **AI agent** named **Goose**. The primary objective was to understand the real-world implications of attacking an AI agent from an external perspective, moving beyond theoretical proof-of-concepts to a full, end-to-end operation aimed at achieving initial execution on an employee's laptop. This initiative was particularly prescient given Block's plans to open-source Goose, necessitating a thorough internal security evaluation.
AI review
Solid end-to-end red team war story with genuine technical texture — invisible Unicode smuggling, system-vs-user prompt injection dynamics, and honest failure analysis make this stand above the average 'we tested an LLM' talk. The social engineering pivot to target the Goose dev team via a fake RTL bug report is the kind of operational creativity that makes a case study worth telling.