agent-airlock

sattyamjjain/agent-airlock

Deny-by-default contract layer for agent tool calls that adds Pydantic strict validation, ghost-argument stripping and retryable fix hints through one decorator, for any agent framework or MCP server

Python Apache-2.0

View on GitHub → Find it in the atlas

Install

pip install "agent-airlock>=0.10.3"

Repository reader

Explore before you clone

Read the project’s README, skills and supporting Markdown here. Rendered view is shown first; source is one click away when you need the exact text.

Fetched from GitHub
Open on GitHub
Loading the project’s README…

Public files are loaded on demand from the repository. The atlas does not copy or modify them.

Screenshot

Screenshot or social card for agent-airlock
GitHub's social card — no screenshot was found for this project, fetched from source rather than copied into this repository.

Platform support

Derived from the project's own README, install route, CI configuration and release assets — not from running it.
PlatformRuns hereOn what evidence
WindowsLikelyInferred from the language or runtime. Nothing in the project says so.
WSL2LikelyInferred from the language or runtime. Nothing in the project says so.
macOSLikelyInferred from the language or runtime. Nothing in the project says so.
LinuxLikelyInferred from the language or runtime. Nothing in the project says so.
DockerYesStated in the project's own README, install route, CI config or release assets.

Where it came from

Named by 1 of the 39 lists the atlas merges.

  • Agent Skill Security

How it is classified

One topic, 3 harnesses. Each link is a prerendered page of everything else in that slice.

Sandbox, Security & GovernanceMCPCodex / OpenAILangChain / LangGraph

Related in Sandbox, Security & Governance

Closest first — projects that plug into the same harnesses, then the ones the most lists agreed on.

  • Immunity AgentPrismorSec/prismorSecurity-focused AI agent runtime for scanning prompt injection, MCP risks, unsafe package installs, and dangerous agent actions before execution
  • Brood Boxstacklok/brood-boxRun AI coding agents (Claude Code, Codex, OpenCode) inside hardware-isolated microVMs with snapshot isolation, egress control, and MCP authorization
  • Node9node9-ai/node9-proxySecurity and governance layer that checks every tool call from coding agents and MCP servers before it runs: credential jail, secret and PII…
  • OWASP Agent Memory GuardOWASP/www-project-agent-memory-guardOWASP reference implementation for ASI06 (Memory Poisoning): runtime defense that screens every agent memory read/write through detectors + a…
  • AegisJustin0504/AegisPre-execution firewall that intercepts, classifies, and blocks agent tool calls before they execute, with a compliance cockpit for real-time…
  • AgentWardenjuangh123/AgentWardenStatic security gate for MCP configurations and AI agent skills, with SHA-256 integrity locking, Ed25519 publisher verification, SARIF output, and…
  • AI Agent Safety Starter Packel-zachariah/ai-agent-safety-starter-packFree repo preflight scanner for Claude Code, Codex, Cursor, and other AI coding-agent runs that flags agent instructions, MCP config, risky shell…
  • Armorer GuardArmorerLabs/Armorer-GuardLocal Rust scanner for AI-agent prompt injection, credential redaction, sensitive-data requests, exfiltration-style text, and dangerous tool-call…