Black Hat · August 20, 2026

Black Hat Asia 2026 | Remote Server, Local Root. Welcome to MCP.

video Agent Security AI Engineering AI Red Teaming

Black Hat Asia 2026 | Remote Server, Local Root. Welcome to MCP. video thumbnail

Why it matters

The researchers reverse the MCP authorization threat model: a malicious remote server can supply dynamic authorization metadata that vulnerable browser, process, or hybrid clients pass into privileged URL-opening and login flows. Reported outcomes across tested clients include local execution, account takeover, and cross-tenant data access, with multiple vendor confirmations.

My takeaway: Bind authorization metadata and redirect targets to a pre-approved server identity, allow only expected HTTPS schemes and origins, and never pass an untrusted URL through a shell or generic OS opener. Re-authorize on metadata changes, isolate local tool execution from OAuth completion, and test browser, CLI, and hybrid clients separately.

Keep exploring

More curated notes connected through Agent Security and AI Engineering.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.