GitLost: When a Public Issue Can Read a Private Repo
GitLost turned a public GitHub issue into a private-repository disclosure. Trace the confused-deputy chain, reproduce it safely, and harden agentic CI.
-
-
GhostApproval: When AI Agent Approval Dialogs Lie
GhostApproval turns a harmless-looking AI agent edit into an out-of-workspace write. Learn the symlink mechanics, safe lab reproduction, detection, and race-resistant defenses.
-
MCP Security: How to Secure Agents, Tools, and Servers
MCP security in practice: the main Model Context Protocol risks, from indirect prompt injection to excessive privileges, and a practical hardening framework for agents, clients, and servers.
-
Attacking Multi-Agent Systems: Rogue Agents and A2A
A practical AI Red Team guide to A2A reconnaissance, canary agent registration, agent-card spoofing, and delegation auditing in an authorized lab.
-
MCP Security: Tools and Permissions in Practice
MCP Security in practice: a safe lab with fictional documents, a mocked local agent, controlled tool exploitation, permissions, schemas, and auditable logs.
-
AI Red Team: 12 Failures Beyond Prompt Injection
A practical AI Red Team guide for testing agents, RAG, memory, tools, and autonomy workflows beyond prompt injection, with checklists, metrics, and controls.
-
AI Recon: LLMs, RAGs, and Agents
Authorized reconnaissance for enterprise AI: map LLMs, RAG pipelines, agents, tools, IAM, APIs, cloud exposure, and evidence without drifting out of scope.
-
Autonomous Pentest Agent: AI, Red Team, and Attack Chains
Autonomous Pentest Agents can accelerate Red Team operations, but they also introduce risk around prompt injection, tool misuse, scope control, evidence quality, and detection.
