Taint Tracking Python Packages

plumb-line-provenance

Stop uncertain data becoming confident-looking results. plumb-line carries provenance, confidence and mock-taint with values through JavaScript and Python, and its review-time checks and GitHub Action catch uncertainty laundered into a claim in AI-assisted code.

capability-reasoning-kernel

Python reference for a CaMeL-like Reasoning Kernel. Control/data-flow separation reduces prompt-injection-to-effect risk when planner input is trusted, the capability policy is correct, and tools enforce it. Topology, not a proof that injection cannot cause an unauthorized effect.

mcpkernel

The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compliant.

interbolt

Blocks AI agent tool calls acting on untrusted data before they cause damage.

tessera-proxy

Contain the blast radius of a prompt injection — a provenance control plane for tool-using agents over MCP.

polytracker

An LLVM-based instrumentation tool for universal taint tracking, dataflow analysis, and tracing.

tessera-rs

Signed provenance labels and taint-tracking policy for LLM agent security. The core library behind AgentMesh.