Part of Leviathan Platform · standalone license available
A prompt-injection detector and a Python egress firewall, for AI agents and automation you build and run yourself. Screen what your tools read and write. Stop them phoning home to the wrong place. Machine identities already outnumber human ones 80:1 in the average enterprise (KPMG, 2026) — this is built for the agents nobody's watching.
What it actually catches
Indirect prompt injection: content your agent reads — a web page, a document, a memory record — carries an instruction it was never meant to follow.
Iron-Thread, a Python egress firewall built on sys.addaudithook, blocks unauthorized outbound connections and subprocess spawns before they leave your infrastructure.
MCP tool and skill-file pinning: a hash-based check that flags a tool or skill's content changing after you first trusted it.
Three modules
register_custom_pattern() — no support ticket, no waiting on us, no editing the package source.Pricing
Flat. Unlimited environments and seats within your org. Covers the library, the CLI, and updates for the year.