Security Consultant ｜ Penetration Tester
A working mum who keeps leveling herself up even after having kids, who loves sharing and being shared with.
Recent
AIAI SecurityMCP
AI Dark Arts (18): Approve Once, Trust Forever? The MCP Client Attack Surface
·1439 words·7 mins
Does approving a config file once mean trusting it forever? From MCPoison and CurXecute to mcp-remote and MCP Inspector, this is how the client side of MCP gets attacked.
AIAI SecurityMCP
AI Dark Arts (17): The Tool Definition Is More Dangerous Than the Tool
·3671 words·18 mins
A tool description nobody reads closely is enough to make an AI hand database tokens to an attacker. Four ways MCP tool poisoning works, and where to stop it when you bring MCP in.
AIAI SecurityMCP
AI Dark Arts (16): MCP Connects the Tools, and the Risk Comes With Them
·1610 words·8 mins
Three roles in Host, Client and Server, three capabilities in tools, resources and prompts. Understand how MCP works and you can see which part the risk arrives through.
AIAI SecurityAI Agent
AI Dark Arts (15): When the AI Acts on Its Own, Taking Apart the Moment an Agent Falls
·2193 words·11 mins
Once an AI has tools, memory and an autonomous loop, a mistake no longer stops at the answer. A tool argument, a sentence in memory, a text file in the project: an agent can promote any of them into an instruction it treats as approved.
AIAI SecurityLLM
AI Dark Arts (14): Find Out What the AI Is Allowed to Do, Then Let It Do the Damage (Excessive Agency)
·1869 words·9 mins
Tools, arguments, execution identity, permission scope. Work through them one at a time and you can usually see where the excessive agency is hiding.