LLMjacking is draining AI budgets faster than most teams notice. Here's how to catch it before the bill doesLLMjacking is draining AI budgets fast -- $46K/day to $500K/month from one leaked key. Free detection tool, no signup required.4 min read·relayshield.hashnode.devJul 27
From Advisory Tool to Mandatory Gate: A LangChain Reference ImplementationOpen-source LangChain wrap_tool_call middleware that blocks unfamiliar MCP server connections behind required security check, not optional tool call.3 min read·relayshield.hashnode.devJul 22
You Asked, We Shipped: 5 New Agent Security Tools, Structured Results, and Two Bugs We Found Along the WayFive new smolagents.Tool checks plus a typed result schema, shipped in direct response to community feedback on the original release.4 min read·relayshield.hashnode.devJul 19
Giving agent frameworks a threat-intel safety check: RelayShield's smolagents toolsFour smolagents.Tool classes that check MCP servers and agent inputs for threats before your AI agent acts with a companion MITRE ATT&CK dataset.3 min read·relayshield.hashnode.devJul 17
RelayShield's Agentic Attack Surface Is Now an MCP ServerFour live MCP tools for AI agent security: server risk checks, prompt-injection breach detection, framework CVE monitoring, and identity risk scoring.2 min read·relayshield.hashnode.devJul 15