Ai Security Governance Python Packages

safeai-static-analyzer

Static analysis and attack-surface scanner for AI agents — SAST for prompts, tools, MCP servers, and agent workflows. Detects capabilities, prompt risks, tool permissions, and governance gaps before deployment.

sayfirst-cli

sayfirst: ask the control plane before an effect

sayfirst

sayfirst: ask the control plane before an effect

ailatch

Encrypted at rest. Executable at runtime. Hidden from AI agents.

shai-harness

Secure Harness AI — the security control plane for production AI agents. SHAI sits between your agent and everything it can touch: tools, external APIs, files, and users. It enforces security at the boundaries — not by hoping the model behaves, but by intercepting every action before it executes.

tokendna-sdk

Runtime identity verification and behavioral trust engine for AI agents. Zero-trust token integrity, session behavioral analytics, and policy enforcement.